Paper Citation Record · LEDGER

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

As of 10 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 2 inbound Pith citation observations for arXiv:2607.07903.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.07903 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-10T15:42:46.392593Z

measured 68 of 68 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T16:59:10.702144Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-08T16:59:12.165147Z

Reference resolution

66 of 66 outbound references displayed

verified exact12
verified fuzzy48
unresolved2
parse uncertain0
malformed identifier3
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 680e0b50-e187-4317-a51e-20bdf9bb804d · outbound

This paper cites Language models are few-shot learners.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Language models are few-shot learners

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.566944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8383f39d-3cce-4125-ab39-1861964c3d2c · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Attention is all you need.Advances in neural information processing systems, 30

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.568568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9c69b763-8d3c-48a5-b556-67661ba8f832 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Explaining and Harnessing Adversarial Examples

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.187453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f1c3ed2e-5048-4696-a2b7-60fac5d7d455 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Towards deep learning models resistant to adversarial attacks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.563775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 59b98507-bd75-4512-8aa5-5b54239ac5ff · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.185136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c27c8f31-64b1-46b0-9b8a-559bb29ca91a · outbound

This paper cites Training language models to follow instructions with human feedback.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Training language models to follow instructions with human feedback

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.570237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1b58cf5e-ea7b-4e69-8c94-62bf1c701a03 · outbound

This paper cites Bridging Interpretability and Robustness Using LIME-Guided Model Refinement.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Bridging Interpretability and Robustness Using LIME-Guided Model Refinement

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.205521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 169b105d-5578-4346-8fd4-1a8ad474fdfd · outbound

This paper cites Multi-scale unrectified push-pull with channel attention for enhanced corruption robustness.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Multi-scale unrectified push-pull with channel attention for enhanced corruption robustness

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.571948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37d3f899-fd79-4665-9b35-54a34dd9b37f · outbound

This paper cites Explainability-guided defense: Attribution-aware model refinement against adversarial data attacks.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Explainability-guided defense: Attribution-aware model refinement against adversarial data attacks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.607238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 601bde07-b71b-497b-ae28-47824b59c8f6 · outbound

This paper cites Representation learning and nature encoded fusion for heterogeneous sensor networks.IEEE Access, 7:39227–39235, 2019.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Representation learning and nature encoded fusion for heterogeneous sensor networks.IEEE Access, 7:39227–39235, 2019

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.622563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 08ace148-a560-4c8f-befa-881010b32548 · outbound

This paper cites Congestion aware dynamic user association in heteroge- neous cellular network: A stochastic decision approach.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Congestion aware dynamic user association in heteroge- neous cellular network: A stochastic decision approach

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.648376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 38a14a71-814c-4758-9711-2cb9b5ec9305 · outbound

This paper cites Explaining the behavior of neuron activations in deep neural networks.Ad Hoc Networks, 111:102346, 2021.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Explaining the behavior of neuron activations in deep neural networks.Ad Hoc Networks, 111:102346, 2021

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.581786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e3ff8f1-6604-4e63-820e-64a19a80671b · outbound

This paper cites Exploration vs exploitation for distributed channel access in cognitive radio networks: A multi-user case study.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Exploration vs exploitation for distributed channel access in cognitive radio networks: A multi-user case study

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.596843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2a0bb3cb-2c49-49a7-b1a4-cd8b05c3e35b · outbound

This paper cites Deep reinforcement learning based computation offloading for mobility-aware edge computing.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Deep reinforcement learning based computation offloading for mobility-aware edge computing

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.573528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 01fb565e-efb7-4e11-966d-9208c0af634f · outbound

This paper cites Improving robustness of deep neural networks via large-difference transformation.Neurocomputing, 450:411–419, 2021.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Improving robustness of deep neural networks via large-difference transformation.Neurocomputing, 450:411–419, 2021

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.577671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation be1049dd-cf8c-461f-b0b2-d8dcf7021290 · outbound

This paper cites Looking beyond content: Modeling and detection of fake news from a social context perspective.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Looking beyond content: Modeling and detection of fake news from a social context perspective

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.646719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 409e11a4-216b-4dfc-845d-1bb5de8c45be · outbound

This paper cites Layer-wise entropy analysis and visualization of neurons activation.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Layer-wise entropy analysis and visualization of neurons activation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.579372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 65310eba-0524-4ea7-98df-0a2f9476d6ff · outbound

This paper cites Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.189844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 47b283e7-d437-4037-ad18-9d223467b674 · outbound

This paper cites Explainability- driven defense: grad-cam-guided model refinement against adversarial threats.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Explainability- driven defense: grad-cam-guided model refinement against adversarial threats

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.650203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b2927e6b-2bb0-4846-8c83-fea33baa0375 · outbound

This paper cites Expert-guided explainable few-shot learning for medical image diagnosis.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Expert-guided explainable few-shot learning for medical image diagnosis

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.565360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 44002a84-b16f-4c4b-b3a4-c475c6d416dc · outbound

This paper cites GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.196757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7d378a65-33d7-4f85-832f-c5ff4b39d6ba · outbound

This paper cites Toward carbon-neutral human ai: Rethinking data, computation, and learning paradigms for sustainable intelligence.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Toward carbon-neutral human ai: Rethinking data, computation, and learning paradigms for sustainable intelligence

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.575486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8a5350e3-9bc5-4180-a294-53ad400d5a1f · outbound

This paper cites Expert-guided explainable few-shot learning with active sample selection for medical image analysis.IEEE Journal of Biomedical and Health Informatics, 2026.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Expert-guided explainable few-shot learning with active sample selection for medical image analysis.IEEE Journal of Biomedical and Health Informatics, 2026

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.643323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cd9bbc7a-77e1-4460-9b12-369abd128e75 · outbound

This paper cites Acting flatterers via llms sycophancy: Combating clickbait with llms opposing-stance reasoning.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Acting flatterers via llms sycophancy: Combating clickbait with llms opposing-stance reasoning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.645010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 56c2b89e-d054-4708-9420-f080785bbee7 · outbound

This paper cites Bridging symmetry and robustness: On the role of equivariance in enhancing adversarial robustness.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Bridging symmetry and robustness: On the role of equivariance in enhancing adversarial robustness

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.651911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1ef30688-2eb1-4f7a-9580-3f2f42d3d60f · outbound

This paper cites Channel- selected stratified nested cross-validation for clinically relevant eeg-based parkinson’s disease detection.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Channel- selected stratified nested cross-validation for clinically relevant eeg-based parkinson’s disease detection

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.638178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 21ce97ec-117e-4049-b15b-71a8d95945cc · outbound

This paper cites Winsor-cam: Human-tunable visual explanations from deep networks via layer-wise winsorization.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Winsor-cam: Human-tunable visual explanations from deep networks via layer-wise winsorization.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.636392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4d088faa-8f00-4701-a457-ed8ef819dd97 · outbound

This paper cites Promoting shape bias in cnns: Frequency-based and contrastive regularization for corruption robustness.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Promoting shape bias in cnns: Frequency-based and contrastive regularization for corruption robustness

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.639983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9826756c-7d04-4d67-abcb-0816e0db9894 · outbound

This paper cites CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.210188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 125e7890-7f5b-484f-9f52-1cd7f5b3d5e7 · outbound

This paper cites Zoom in: An introduction to circuits.Distill, 5(3):e00024–001.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Zoom in: An introduction to circuits.Distill, 5(3):e00024–001

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.632952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e02460d-b20c-4e45-877c-28c239cd849f · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs A mathematical framework for transformer circuits.Transformer Circuits Thread

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.634679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d3ef84b-4c08-426c-bd4a-f016d587c3ad · outbound

This paper cites an unresolved cited work.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-07-10T15:47:23.641528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f64d98e3-b05d-4a52-ac51-21ffc217c163 · outbound

This paper cites Axiomatic attribution for deep networks.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Axiomatic attribution for deep networks

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.627734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19c3e22f-0b0f-4cb3-bd67-a265097642f9 · outbound

This paper cites Intriguing properties of neural networks.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Intriguing properties of neural networks

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.207919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9d1f8654-46f5-4d79-b9f4-af89aeedf039 · outbound

This paper cites Towards evaluating the robustness of neural networks.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Towards evaluating the robustness of neural networks

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.629384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 696d66d3-169e-44dc-b7eb-64a09802ec10 · outbound

This paper cites Visual adversarial examples jailbreak aligned large language models.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Visual adversarial examples jailbreak aligned large language models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.625900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 418d9386-7a86-4bdb-ac2a-3bacb33122ee · outbound

This paper cites AutoDAN: Interpretable gradient-based adversarial attacks on large language models.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs AutoDAN: Interpretable gradient-based adversarial attacks on large language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.631154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2f013e77-14d3-4bad-8f75-077096bd4231 · outbound

This paper cites DOI:10.23915/distill.00010.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs DOI:10.23915/distill.00010

Reference 38

Resolution: metadata mismatch; doi, observed 2026-07-10T15:47:22.952574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 834c07d4-92ff-4961-8321-d67b623b6f49 · outbound

This paper cites In-context learning and induction heads.Transformer Circuits Thread.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs In-context learning and induction heads.Transformer Circuits Thread

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.653540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e9fd6d66-7bb3-4da6-90b3-89fb35b85ab4 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Sparse autoencoders find highly interpretable features in language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.619321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 009f8fb8-8db9-4acb-8ff1-5628c34fbb89 · outbound

This paper cites Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.203361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5905a272-3c72-45d8-b89e-9b09ca947f98 · outbound

This paper cites A unified approach to interpreting model predictions.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs A unified approach to interpreting model predictions

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.620873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b3b1e879-d152-4107-99f6-b041cf7d6430 · outbound

This paper cites why should i trust you?.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs why should i trust you?

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.624246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c1ac42e5-49e7-4172-b397-bfc69a7a492f · outbound

This paper cites Attribution patching: Activation patching at industrial scale.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Attribution patching: Activation patching at industrial scale

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.614430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9e490a52-f32a-4541-ab21-a0c902bcf5e2 · outbound

This paper cites Causal abstraction: A theoretical foundation for mechanistic interpretability.Journal of Machine Learning Research, 26(83):1–64, 2025.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Causal abstraction: A theoretical foundation for mechanistic interpretability.Journal of Machine Learning Research, 26(83):1–64, 2025

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.616097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 50fd132c-5ad3-4a3e-9f9f-c77909e573fc · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis.Advances in neural information processing systems, 33:12388–12401.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Investigating gender bias in language models using causal mediation analysis.Advances in neural information processing systems, 33:12388–12401

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.612655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ce825ff0-56c2-4612-98cd-990467af4351 · outbound

This paper cites Locating and editing factual associations in gpt.Advances in neural information processing systems, 35:17359–17372.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Locating and editing factual associations in gpt.Advances in neural information processing systems, 35:17359–17372

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.617762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3185777b-bdb9-46c8-8c98-75c128dab86c · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs LLaMA: Open and Efficient Foundation Language Models

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.201157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8b718b0-36eb-476e-9798-19ee400e2889 · outbound

This paper cites Jailbroken: How does llm safety training fail?Advances in neural information processing systems, 36:80079–80110, 2023.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Jailbroken: How does llm safety training fail?Advances in neural information processing systems, 36:80079–80110, 2023

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.605525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 167d61a9-581f-43ff-a259-c3e74f7c7326 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.198943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation da099723-6c95-48f6-8c9a-fb37b679a2fb · outbound

This paper cites Adversarial examples are not bugs, they are features.Advances in neural information processing systems, 32, 2019.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Adversarial examples are not bugs, they are features.Advances in neural information processing systems, 32, 2019

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.609025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f6dd829d-a2b0-4d9b-8998-b4a26c6e62d7 · outbound

This paper cites Learning important features through propagating activation differences.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Learning important features through propagating activation differences

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.600092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 979d68bc-b92e-48b9-8b2d-8381f37b570d · outbound

This paper cites Many-shot jailbreaking.Advances in Neural Information Processing Systems, 37:129696–129742.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Many-shot jailbreaking.Advances in Neural Information Processing Systems, 37:129696–129742

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.601830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b3167a1e-fa7b-4ee4-8bd8-ab8dabe259fe · outbound

This paper cites Cambridge university press.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Cambridge university press

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.603584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c9046830-c70d-4c03-9f5b-7f95a9a6d6a1 · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.Advances in Neural Information Processing Systems, 36:16318–16352.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Towards automated circuit discovery for mechanistic interpretability.Advances in Neural Information Processing Systems, 36:16318–16352

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.610848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e795c348-4efc-4d42-8f9d-5af2832ea141 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.192014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7f1d3f38-1633-4655-bdb2-ef449938f344 · outbound

This paper cites Adversarial examples are not easily detected: Bypassing ten detection methods.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Adversarial examples are not easily detected: Bypassing ten detection methods

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.595111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0e9f695-dcd0-4105-af07-c4a89dd42499 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:47:23.194167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d18e636b-2ada-4ea8-a7c7-9bc4110bc85d · outbound

This paper cites pathway suppression.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs pathway suppression

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.590152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bbdb9734-898d-4eb7-9835-06164d8bc6c5 · outbound

This paper cites 1.8 in clean) despite having fewer total nodes, suggesting remaining features are hyperactivated to compensate for missing pathways.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs 1.8 in clean) despite having fewer total nodes, suggesting remaining features are hyperactivated to compensate for missing pathways

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.591831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 93585ef2-b34b-4345-a227-b24445eab099 · outbound

This paper cites Write a poem about nature.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Write a poem about nature

Reference 62

Resolution: malformed identifier; raw_fallback, observed 2026-07-10T15:47:23.586419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 306f5feb-03f5-4ce9-ae21-5b2b940090a0 · outbound

This paper cites This is consistent with the PCA analysis in Figure 5 showing that attack trajectories diverge most strongly at layer 15.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs This is consistent with the PCA analysis in Figure 5 showing that attack trajectories diverge most strongly at layer 15

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.588591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 58480b53-d3ea-45b0-85a0-7983d5ebe463 · outbound

This paper cites Tell me how to make a cake.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Tell me how to make a cake

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:47:23.593281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba11b773-9795-4628-b809-d633289e3bb0 · outbound

This paper cites Tell me how to make a cake.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Tell me how to make a cake

Reference 65

Resolution: malformed identifier; raw_fallback, observed 2026-07-10T15:47:23.598410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 22d6d1b7-e719-42bf-ad5c-9738d335deeb · outbound

This paper cites an unresolved cited work.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Unresolved cited work

Reference 66

Resolution: malformed identifier; raw_fallback, observed 2026-07-10T15:47:23.583262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5b38be97-4696-49e6-8491-2bf4370cbcce · outbound

This paper cites an unresolved cited work.

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-07-10T15:47:23.584852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 6c8cb14b-cdb1-459e-bbc6-6bdb6cde63c6 · inbound

Learning to Transmit: Volatility-Aware Predictive Communication for Energy-Efficient IoT Networks cites this paper.

Learning to Transmit: Volatility-Aware Predictive Communication for Energy-Efficient IoT Networks Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T12:21:53.334309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1887b201-8937-4113-8006-45742510055d · inbound

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI cites this paper.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:59:12.188293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.