Paper Citation Record · LEDGER

Towards eliciting latent knowledge from LLMs with mechanistic interpretability

As of 10 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 9 inbound Pith citation observations for arXiv:2505.14352.

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

pith.paper-citation-record.v1
2505.14352 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:40:07.861843Z

measured 39 of 39 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 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:20:51.989267Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

30 of 30 outbound references displayed

verified exact1
verified fuzzy13
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 1f0d0b3f-737f-484a-85b1-811e08771f24 · outbound

This paper cites write newline.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.057222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511f238a-e3aa-4478-8dce-1dd08fed1d9a · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Tell me about yourself: LLMs are aware of their learned behaviors

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.176888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b876a4f-14aa-499c-9a3a-99deede786ab · outbound

This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned llms.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Emergent misalignment: Narrow finetuning can produce broadly misaligned llms

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.246250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceccbf25-6bf5-4eaf-b38f-82f0527d3524 · outbound

This paper cites E., Hume, T., Carter, S., Henighan, T., and Olah, C.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability E., Hume, T., Carter, S., Henighan, T., and Olah, C

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.336601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce6d09c6-23cc-41fb-a75f-90b362471e25 · outbound

This paper cites Eliciting latent knowledge: How to tell if your eyes deceive you, 2021.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Eliciting latent knowledge: How to tell if your eyes deceive you, 2021

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:10.979962Z

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 8ab3fae9-90a7-4b18-935f-485cfe3fc634 · outbound

This paper cites F., Leike, J., Brown, T., Martic, M., Legg, S., and Amodei, D.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability F., Leike, J., Brown, T., Martic, M., Legg, S., and Amodei, D

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.533081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ad1cdce-3136-4de4-8d8a-f201ef897d63 · outbound

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

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.657362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9020be08-2811-4fb1-9c81-85823fbfd8f9 · outbound

This paper cites Safe RLHF : Safe reinforcement learning from human feedback.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Safe RLHF : Safe reinforcement learning from human feedback

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:10.789023Z

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 2f1fc3d7-4b82-437e-9b8f-da650e9b9df9 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Qlora: Efficient finetuning of quantized llms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:05.816404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8419faf-5ad4-4c82-9089-e10388bd00af · outbound

This paper cites Pal: Program-aided language models.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Pal: Program-aided language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:10.544027Z

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 f78732ec-7c97-41db-acb6-5b6f3c15ed75 · outbound

This paper cites Gemini 2.5 flash, 2025 a.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Gemini 2.5 flash, 2025 a

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:10.346882Z

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 c5f075c8-433c-4927-8594-ea3ab04015d6 · outbound

This paper cites Gemini 2.5 pro preview, 2025 b.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Gemini 2.5 pro preview, 2025 b

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:10.136279Z

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 b5635376-a01a-460b-8ad0-e949039a0f6c · outbound

This paper cites Alignment faking in large language models.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Alignment faking in large language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:06.156563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2b0c15-274a-432d-a95d-c421c32a8667 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:06.249074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dc4628e-ae13-40c4-a7fa-3fa88ab731d5 · outbound

This paper cites and Lee, S.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability and Lee, S

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.952659Z

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 16de2527-ffb6-46a0-801c-457ab90bc719 · outbound

This paper cites u chemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., G \.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability u chemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., G \

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.818736Z

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 480279d4-bbad-4752-9cec-e4b7594543c9 · outbound

This paper cites M., Bommarito, M.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability M., Bommarito, M

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.674256Z

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 13023214-b0bf-4312-be60-747afb101da2 · outbound

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

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:06.584693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4523999c-11ea-4675-8629-f91213f4ebe6 · outbound

This paper cites Auditing language models for hidden objectives.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Auditing language models for hidden objectives

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:06.682295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac39182b-c4bf-4d4d-9319-78b89bf67f87 · outbound

This paper cites Frontier Models are Capable of In-context Scheming.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Frontier Models are Capable of In-context Scheming

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:06.782520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68671958-3532-4304-b1c0-16ed2186ead8 · outbound

This paper cites interpreting gpt: the logit lens.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability interpreting gpt: the logit lens

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.522399Z

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 efdf8ba3-4011-479b-b770-f283ec91767b · outbound

This paper cites Learning to reason with llms, 2024b.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Learning to reason with llms, 2024b

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.328159Z

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 1a02bb6a-e6a2-418c-8618-b60bfa998db6 · outbound

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

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Training language models to follow instructions with human feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:07.112022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f6bfe05-6f84-46d8-91cd-3a1ca2a3bbbe · outbound

This paper cites D., Ermon, S., and Finn, C.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability D., Ermon, S., and Finn, C

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.166740Z

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 49d393c5-a973-41d8-ae91-34bfd73cfeda · outbound

This paper cites LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:40:08.100475Z

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 7a6f0fd4-9efd-4e5a-82cd-e68e69c925ce · outbound

This paper cites Top 1000 english nouns, 2019.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Top 1000 english nouns, 2019

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:09.063228Z

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 87906699-feee-48b8-9fe9-90d16caa5973 · outbound

This paper cites Large language models can strategically deceive their users when put under pressure.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Large language models can strategically deceive their users when put under pressure

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:40:08.902763Z

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 12d7963d-ac67-4556-8d4c-d04a4424e592 · outbound

This paper cites an unresolved cited work.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:07.649664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e8a314b-57e8-4e7d-923c-ea400b0faca4 · outbound

This paper cites an unresolved cited work.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:40:08.587883Z

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 6ee307d4-e2d9-4355-ad8b-597a447b6ec0 · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability N., Kaiser, ., and Polosukhin, I

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:07.861843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b4bd3ba3-9c28-48ce-82c3-e71a7d58af84 · inbound

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy cites this paper.

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T22:20:51.989267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e6064b-8eca-414d-913f-f9b0a427f6ea · inbound

DECOR: Auditing LLM Deception via Information Manipulation Theory cites this paper.

DECOR: Auditing LLM Deception via Information Manipulation Theory Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T06:28:05.444725Z

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 71882747-c6a5-4999-bdb2-b6a74edf1618 · inbound

Building Better Activation Oracles cites this paper.

Building Better Activation Oracles Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:24:45.078140Z

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 bf2dbefc-e764-4a38-9b8d-6660d1c8a799 · inbound

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms cites this paper.

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.307763Z

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 a44a5147-ccd4-4129-a339-7880f3ca094a · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:38:55.997805Z

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 3a8b2a06-b7ed-42ab-b5fc-883db645c7ee · inbound

"Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo cites this paper.

"Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:16:58.191057Z

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 b9cd5712-4558-422c-9c58-77fc742c2630 · inbound

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology cites this paper.

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:08.173995Z

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 76e1f9be-c3ec-4f0e-9a94-c8040b4a08fe · inbound

MUX: Continuous Reasoning via Multiplexed Tokens cites this paper.

MUX: Continuous Reasoning via Multiplexed Tokens Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T13:43:03.078595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4e3907-474c-4909-9ba9-029b28afc797 · inbound

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles cites this paper.

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T23:56:50.935284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.