Paper Citation Record · LEDGER

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

As of 17 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 7 inbound Pith citation observations for arXiv:2411.11114.

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

pith.paper-citation-record.v1
2411.11114 v2

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:00:24.128580Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:55:12.949520Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T10:58:13.598332Z

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy1
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aea6d20c-50be-4eb3-9c0e-0059001255b1 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:25.104831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 20513e0c-828e-4e31-94db-cc118ea2112b · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:25.084334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9f78405e-baf5-4d77-80a5-1cc14b926903 · outbound

This paper cites Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.917123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17a7d23f-764c-4c72-854b-b8f8c83f8302 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.923074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2120086a-c82e-41ad-bc27-8b54ec9b8e1f · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.927972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 391ba199-e58a-44a0-80a8-a5859ff5f204 · outbound

This paper cites Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.933361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff15974-48b1-49a4-a4d0-43b689644a69 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.938674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8b5c09-8b66-4e7b-8a63-557e5a556de3 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:25.053842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 65571498-3f47-4f9b-a55e-179dca7bb36c · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:25.036275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a28f6e12-e5e6-4687-9866-aaf9dd5c3454 · outbound

This paper cites arXiv preprint arXiv:2406.14144 (2024).

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit arXiv preprint arXiv:2406.14144 (2024)

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.949385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd31a0d-acf9-47da-b4aa-549ca777d09a · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.965731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31459bd3-ea3a-4dac-af3a-1ee89f9c2c49 · outbound

This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.959599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dcdfa34-d943-47c7-aec6-89bdce086948 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:25.005905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b9d3319e-0d86-4692-bc98-20ccb3c9e710 · outbound

This paper cites Language Models Represent Space and Time.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Language Models Represent Space and Time

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.971125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdbc6cb-1eec-4e57-9a6a-94ab288e4b6a · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:24.985945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0baa5949-e5bc-421d-a279-0cf78d957860 · outbound

This paper cites Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.981651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2319fbaf-c196-4914-94a2-c04187151c2f · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.999396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c816325b-4d41-44e1-a458-21a771ebc36f · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.992798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8a4e7b-4fb6-4d94-b62b-c7a88358fc12 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.017557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 012b4355-2af5-4645-98b2-652d325b4c1d · outbound

This paper cites Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.027619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de58bf13-3873-4cbb-8fe1-c49c51efe537 · outbound

This paper cites Safety Layers in Aligned Large Language Models: The Key to LLM Security.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Safety Layers in Aligned Large Language Models: The Key to LLM Security

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.011689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbe7ae2-a7c0-4835-8db1-f06011f80d3d · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.038197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff4698a-92c1-49ce-b37e-1b2914ac5b3a · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.022564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c965ba9-4ce4-485d-aa9a-e5fd371a6d84 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.050384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d0fda0d-247a-46b5-a9b9-f1981a431ec7 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.032648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed9e3d40-894b-4a94-b845-40c112bbcbf4 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.060047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b972e6d-e5d3-441d-8bb9-d3fe50f23250 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.044253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5abf235e-9b44-443c-89b9-9aa8c6f97ba6 · outbound

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

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit LLaMA: Open and Efficient Foundation Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.072614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c38ef7-774d-46cb-814b-c724d458d245 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:00:24.926300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4cba5927-580a-4153-97b0-c150d2c24170 · outbound

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

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.083459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c11050b-b03d-425e-a3cd-4591d5266737 · outbound

This paper cites Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.065559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67518f73-47fd-4038-a982-8c8e67e489c2 · outbound

This paper cites Qwen2 Technical Report.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Qwen2 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.095222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb2c7352-88d0-4b9a-a4e1-22edd461c021 · outbound

This paper cites Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.077901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c4ada6d-e67e-4bbb-a227-55fe0ac53813 · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.106786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27582156-73ed-4860-b692-a17354f0e3d2 · outbound

This paper cites an unresolved cited work.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.089167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 800db129-f8ac-4012-9812-1e8d11a6ae4b · outbound

This paper cites How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.118281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7192eb54-c611-4c86-a3be-157dbee2c391 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.101523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 272b65e6-fe0c-4507-bf7a-dd379ce0500a · outbound

This paper cites Causality Analysis for Evaluating the Security of Large Language Models.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Causality Analysis for Evaluating the Security of Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.113144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f016b76-ace9-4cd8-a11c-8c4959ebc4b9 · outbound

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

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.123292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560f71c5-6575-42af-bdbd-2489e374e074 · outbound

This paper cites In the final layer, the characters among all layers discuss which specific and practical commands, tools, or steps should used.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit In the final layer, the characters among all layers discuss which specific and practical commands, tools, or steps should used

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:00:24.883210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a1cb033-70a8-4b7d-9da3-895ebcad060e · outbound

This paper cites Generative Judge for Evaluating Alignment.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Generative Judge for Evaluating Alignment

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:24.004869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 134a2f66-5d04-4480-842e-30d88f493382 · outbound

This paper cites AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers.

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T19:00:23.911434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ee5da2d0-02bc-452c-8217-0b60cd592731 · inbound

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models cites this paper.

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T05:55:12.949520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88038503-14c4-4009-9c3c-29ad01236c71 · inbound

SATORI: Static Test Oracle Generation for REST APIs cites this paper.

SATORI: Static Test Oracle Generation for REST APIs JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T17:26:48.640745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7b93f94-ee25-4fca-9e21-9d33ae828b92 · inbound

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models cites this paper.

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T10:32:27.731531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8214683-746e-44d0-b3c0-bf2d6730c954 · inbound

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision cites this paper.

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:30:51.229691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b28a0e71-81ea-43d9-8327-c84f06dc99d5 · inbound

Why Do Large Language Models Generate Harmful Content? cites this paper.

Why Do Large Language Models Generate Harmful Content? JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:21:04.483275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 143cc986-2430-4419-8c73-1bc6f6e98149 · inbound

Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off cites this paper.

Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T01:46:14.934203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 57e7a767-846a-46c1-8564-d6a199678b18 · inbound

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction cites this paper.

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:58:13.600614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.