Paper Citation Record · LEDGER

Towards Automated Circuit Discovery for Mechanistic Interpretability

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 40 inbound Pith citation observations for arXiv:2304.14997.

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

pith.paper-citation-record.v1
2304.14997 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 40 of 40 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:57:30.012689Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

32
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation b618ee32-d664-46f8-9765-d3fc53dce4d8 · inbound

Sparse Autoencoders Find Highly Interpretable Features in Language Models cites this paper.

Sparse Autoencoders Find Highly Interpretable Features in Language Models Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-24T06:44:02.183406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 58bcce53-5c39-481b-9cde-cd4d88398c66 · inbound

How to use and interpret activation patching cites this paper.

How to use and interpret activation patching Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:34:06.914206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 82f206c9-eff3-4bc6-a355-f557798bbec4 · inbound

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 cites this paper.

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:47:20.036422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dbb44eab-a1fb-4e01-b41e-698aeab39382 · inbound

AI Governance through Markets cites this paper.

AI Governance through Markets Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T04:36:43.804112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69061fed-e49d-4c2b-8b98-dd09645abde2 · inbound

Transcoders Beat Sparse Autoencoders for Interpretability cites this paper.

Transcoders Beat Sparse Autoencoders for Interpretability Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.827765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c689dd0f-0093-4237-bcae-33c9267541da · inbound

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning cites this paper.

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:34.145737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47bd69df-1e0c-4a37-a7f3-eab94ca8412b · inbound

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video cites this paper.

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:57:30.012689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bbc4ffc-89aa-4a8a-9228-f21bfc00c894 · inbound

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii cites this paper.

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T04:25:05.678871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0e0547-91ee-4238-a000-c40b0245b7fd · inbound

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence cites this paper.

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:54.375524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a045aa9-53ee-46d0-948d-5305715a72bb · inbound

Circuit Stability Characterizes Language Model Generalization cites this paper.

Circuit Stability Characterizes Language Model Generalization Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:36.560849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2bfb6fd-c972-4e1d-9227-d18828cdc1fd · inbound

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits cites this paper.

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T17:37:55.872665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e2e582d-84cf-4b6f-af44-3536a0ba7fa2 · inbound

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content cites this paper.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.149122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5b7cd1b-4e74-4a8a-89b1-e04ac683ef05 · inbound

Language Model Circuits Are Sparse in the Neuron Basis cites this paper.

Language Model Circuits Are Sparse in the Neuron Basis Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T06:35:33.648793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935921d7-9ffd-4335-8944-20ba480364d2 · inbound

From Features to Actions: Explainability in Traditional and Agentic AI Systems cites this paper.

From Features to Actions: Explainability in Traditional and Agentic AI Systems Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:50:15.149847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc8261f-3111-4f91-8dbd-e8464cac9ab0 · inbound

Enhancing Multi-Robot Exploration Using Probabilistic Frontier Prioritization with Dirichlet Process Gaussian Mixtures cites this paper.

Enhancing Multi-Robot Exploration Using Probabilistic Frontier Prioritization with Dirichlet Process Gaussian Mixtures Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T13:35:02.428552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e34a12d1-2961-4a5c-9701-c9a274f3d1eb · inbound

STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models cites this paper.

STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:18:13.386322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 614ee7ab-659c-4a58-9fb8-20b114024c09 · inbound

Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation cites this paper.

Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:01:05.319756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eed9b08f-35e9-45fa-8c7c-311d6d5efd39 · inbound

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers cites this paper.

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-08T21:39:24.472752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a28a9de0-9ca5-4305-b7e9-5447e21d31af · inbound

Eliciting associations between clinical variables from LLMs via comparison questions across populations cites this paper.

Eliciting associations between clinical variables from LLMs via comparison questions across populations Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-08T21:34:13.339991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9c2d2b64-9fae-4120-ac89-28b8c913dea6 · inbound

Dissecting Jet-Tagger Through Mechanistic Interpretability cites this paper.

Dissecting Jet-Tagger Through Mechanistic Interpretability Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:51:22.769645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 647671f6-376d-4840-ad97-dd99c985d888 · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:17:53.992568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b9f33560-3e0f-4132-a279-c09b14bc4ff0 · inbound

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy cites this paper.

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:07:53.882972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3621a9d6-d6ff-4329-8ec4-5fb2336b0556 · inbound

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy cites this paper.

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T21:33:46.486479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bf50b9f1-1011-4798-89dc-6094a9ed5059 · inbound

How to Interpret Agent Behavior cites this paper.

How to Interpret Agent Behavior Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:27:35.897382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2e7032fa-05a0-4eb4-99da-673ba84149d2 · inbound

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability cites this paper.

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T03:19:43.704142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3928ba05-de27-4b63-89f3-4511d7010a7c · inbound

From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models cites this paper.

From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:01:11.983212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a51b679d-5aa3-48e3-a009-2b59bdf01ae2 · inbound

MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models cites this paper.

MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 1

Resolution: malformed identifier; no resolver link, observed 2026-07-13T09:07:13.817929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef6806d-c57c-4110-a422-31cb39da382a · inbound

Explaining Attention with Program Synthesis cites this paper.

Explaining Attention with Program Synthesis Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:59:21.019640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8176dc3b-dbf9-46e6-bfec-a7bdc664a3ce · inbound

Explaining Attention with Program Synthesis cites this paper.

Explaining Attention with Program Synthesis Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-30T11:54:39.156734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b0da2d27-f41d-4260-9491-cc950260ffc4 · inbound

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination cites this paper.

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:26:55.883819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 44d33f06-a2b5-4278-847a-5d8abde742ba · inbound

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning cites this paper.

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-09T15:06:18.046309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 625e0109-428b-4739-9faf-aba305a4a487 · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T10:39:48.831071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d1c8ec-a8e5-478a-a2af-36ec007339b5 · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 154

Resolution: unresolved; no resolver link, observed 2026-08-02T10:40:01.245170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bfc993f-2e67-4949-8221-d77f98e3a6f7 · inbound

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures cites this paper.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:29.659933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a6bc1d-8b09-4c55-ae82-bcf4390311af · inbound

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models cites this paper.

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T14:26:49.070810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7406690-c367-4403-b650-4b17f2da9be3 · inbound

IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning cites this paper.

IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T05:25:22.684556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72e03d84-8e20-482a-970c-1563cb3fd42b · inbound

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory cites this paper.

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-31T23:35:49.065747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8f5fb39-df29-424a-a215-ab20e6bdcd34 · inbound

LAWFUL: Law-Aligned Witness for Faithful Use of Latents cites this paper.

LAWFUL: Law-Aligned Witness for Faithful Use of Latents Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T00:47:35.968722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5066514a-4879-41ff-a1c2-117d1a2d8566 · inbound

Sparse Weight Decomposition for Efficient Circuit Extraction cites this paper.

Sparse Weight Decomposition for Efficient Circuit Extraction Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.381843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5daefd8d-c7e4-4f95-be1a-2feb7a3718c2 · inbound

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation cites this paper.

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T13:29:00.101336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.