Paper Citation Record · LEDGER

AtP*: An efficient and scalable method for localizing LLM behaviour to components

As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 35 inbound Pith citation observations for arXiv:2403.00745.

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

pith.paper-citation-record.v1
2403.00745 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 35 of 35 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:44:55.426570Z

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

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation cb6c96a8-3327-4d2b-8554-8db5b559bc76 · inbound

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models cites this paper.

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T13:15:10.715282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a9fc4b30-04b2-4085-9193-6378f20f8b78 · inbound

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers cites this paper.

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T21:29:17.070133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3476cbbb-24e0-4dfd-9492-ed5e5f5c9ffd · inbound

Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models cites this paper.

Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T20:26:42.874194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc3b048-ff07-46d0-b532-91eb721ae6a2 · inbound

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition cites this paper.

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T14:55:02.076326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1feee041-aced-46ba-90f2-5eef86974bed · inbound

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

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:34.935332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61541782-adb1-407b-872e-f46ea5afb7cc · inbound

Language Models Use Trigonometry to Do Addition cites this paper.

Language Models Use Trigonometry to Do Addition AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T17:29:00.164619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 178e618b-1e7b-4d39-bdf7-12e5b6a543dc · inbound

Circuit Stability Characterizes Language Model Generalization cites this paper.

Circuit Stability Characterizes Language Model Generalization AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:38.272914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1215c80c-f397-4304-89cd-3a2e21d794a6 · inbound

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety cites this paper.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.388763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c63bfe-0596-4ab6-bba2-962ba17708a8 · inbound

Steering Conceptual Bias via Transformer Latent-Subspace Activation cites this paper.

Steering Conceptual Bias via Transformer Latent-Subspace Activation AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.426570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 730a5abb-3bfe-4ef2-9158-8b517b1b6833 · inbound

Stochastic Parameter Decomposition cites this paper.

Stochastic Parameter Decomposition AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T22:48:37.292501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 985b5627-8aaa-47aa-9bd3-5ba6ef2d94fe · inbound

Can Interpretation Predict Behavior on Unseen Data? cites this paper.

Can Interpretation Predict Behavior on Unseen Data? AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:28.998137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75fe8a39-8c9d-4395-a5d8-e911148a90ba · 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 AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T17:37:55.128637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e5023d-d217-4135-b3f4-dfb4296ce340 · inbound

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs cites this paper.

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:46:09.779273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b7172ed3-f045-4d23-963d-bba7affc696b · inbound

Weight Patching: Toward Source-Level Mechanistic Localization in LLMs cites this paper.

Weight Patching: Toward Source-Level Mechanistic Localization in LLMs AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:35:26.506038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ef1a1761-b1f8-49dd-859b-44b974575a16 · inbound

Cell-Based Representation of Relational Binding in Language Models cites this paper.

Cell-Based Representation of Relational Binding in Language Models AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:06:04.689930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation af8e2676-9e65-4045-80f5-1b3dee73b568 · inbound

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure cites this paper.

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:21:19.001882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 60b445b2-3634-42d4-8bd6-3db03aa0f56d · inbound

How LLMs Are Persuaded: A Few Attention Heads, Rerouted cites this paper.

How LLMs Are Persuaded: A Few Attention Heads, Rerouted AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:24.280719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5a01933e-9258-4752-82aa-db9a0d792ccd · inbound

Not How Many, But Which: Parameter Placement in Low-Rank Adaptation cites this paper.

Not How Many, But Which: Parameter Placement in Low-Rank Adaptation AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:17:23.202341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ed325fa1-5b59-4798-bcc5-af82bdf3da05 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:59:28.809227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9b3f5625-0118-460a-a276-7614e5b53e05 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:59:45.276290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3b120abc-9cfa-44c0-b74b-86b5886ac5a6 · inbound

Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m cites this paper.

Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:14:45.528877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4fbca113-87b9-49e8-b0ef-13689a794349 · inbound

Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability cites this paper.

Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T12:04:38.232924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 20f6d7b7-97b2-4622-8e0b-86c688ee4fb0 · inbound

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet cites this paper.

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T07:53:13.422088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dfbe8c23-2036-40e9-bb70-a153aefae165 · inbound

Subliminal Learning is a LoRA Artifact cites this paper.

Subliminal Learning is a LoRA Artifact AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-28T20:42:37.588014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 798b7c1b-5a32-4a70-8b18-838af695c2a5 · inbound

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery cites this paper.

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T01:51:28.966057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 65472b2b-5d9b-42d9-890d-f62ae5d12c07 · inbound

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective cites this paper.

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:57:23.086842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2997d91a-32dc-4312-91a4-75a6063e6f3c · inbound

When Attribution Patching Lies: Diagnosis and a Second-Order Correction cites this paper.

When Attribution Patching Lies: Diagnosis and a Second-Order Correction AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T16:07:09.056752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a03226b5-68db-4d60-8ba7-6a5d3d399e43 · inbound

Localizing Anchoring Pathways in Language Models cites this paper.

Localizing Anchoring Pathways in Language Models AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:28:31.353144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 313d37f0-6013-4bd7-abb9-11a3ac5410bc · inbound

Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components cites this paper.

Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:28:44.697122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cf7af405-a3e5-4ff6-b25e-517c8c9f69e7 · inbound

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability cites this paper.

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-10T09:06:59.176399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 92b12914-ff66-4388-b3c1-3292c675f2f1 · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.600435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 529e8a8c-b88a-4f1f-ba12-4ab4cd46af65 · inbound

Circuit Claims Depend on What Is Extracted and How It Is Compared cites this paper.

Circuit Claims Depend on What Is Extracted and How It Is Compared AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T14:03:18.016818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ffb5c0-1972-4a93-9f01-27fb72ec9e53 · inbound

Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training cites this paper.

Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T00:23:26.696774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74cab79d-a110-4087-b37f-9a423274db9a · inbound

Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability cites this paper.

Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T04:21:09.465395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b10829-4f1c-4001-9a7c-2183dbf21c1c · 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 AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-14T13:29:00.188391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.