Paper Citation Record · LEDGER

Scaling laws for activation steering with Llama 2 models and refusal mechanisms

As of 17 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2507.11771.

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

pith.paper-citation-record.v1
2507.11771 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:05:04.820314Z

measured 17 of 17 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:25:43.377432Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T00:25:43.489612Z

Reference resolution

16 of 16 outbound references displayed

verified exact0
verified fuzzy3
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4047946d-31b8-4f67-8717-90c8410077c6 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Mechanistic Interpretability for AI Safety -- A Review

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:03.622889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62cb6a61-d972-474a-b3f4-cee12f636adc · outbound

This paper cites A toy model of universality: Reverse engineering how networks learn group operations.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms A toy model of universality: Reverse engineering how networks learn group operations

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:05:05.434920Z

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 601b57e4-96ce-48b6-a9da-67fd7168c73d · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Towards automated circuit discovery for mechanistic interpretability

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:03.761144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90722fc7-0fda-4edf-a2bb-16fcfada84b8 · outbound

This paper cites Toy Models of Superposition.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Toy Models of Superposition

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:03.845054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a901bc-7b60-4059-94c4-2b8109e29806 · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:03.916915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14e88341-cb6e-43bd-92b4-c920351d5f2d · outbound

This paper cites Datamodels: Predicting Predictions from Training Data.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Datamodels: Predicting Predictions from Training Data

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:03.982552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df3b9283-6c2b-4e5d-8145-24e472089997 · outbound

This paper cites TRAK: Attributing Model Behavior at Scale.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms TRAK: Attributing Model Behavior at Scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.041203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f63daaa-e723-46f2-9e5f-6a78cfe93ced · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Steering Llama 2 via Contrastive Activation Addition

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.150422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 253994b4-5436-405c-87b1-8615443815ef · outbound

This paper cites M., Ilyas, A., and Madry, A.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms M., Ilyas, A., and Madry, A

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:05:05.297143Z

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 7b4fcd37-a3f9-40dd-880e-4f48ea5a59ac · outbound

This paper cites Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:05:05.162627Z

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 d045c2ef-959a-4761-9493-bba4b61e0933 · outbound

This paper cites Steering Language Models With Activation Engineering.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Steering Language Models With Activation Engineering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.423071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2201a38b-4fcd-4c41-8296-90544649bed1 · outbound

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

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.509549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd26905-b1d2-4e65-a081-912f6b562194 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.599235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d183bf-d72a-4cdf-9fbd-c045b2f050d9 · outbound

This paper cites Knowledge Conflicts for LLMs: A Survey.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Knowledge Conflicts for LLMs: A Survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.694957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 182fc9f9-0577-4c67-9158-41413fef0fbf · outbound

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

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.749036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2462df79-733e-4f0a-8d58-4bd941ba5c39 · outbound

This paper cites write newline.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms write newline

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.820314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 472cee5e-8c34-4763-958d-f25e41e2c27e · inbound

When Is a Steerable Concept Representation Real? Measurement Confounds in a Cross-Family Audit of Neuroscience Parallels in LLMs cites this paper.

When Is a Steerable Concept Representation Real? Measurement Confounds in a Cross-Family Audit of Neuroscience Parallels in LLMs Scaling laws for activation steering with Llama 2 models and refusal mechanisms

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-08-12T00:25:43.493544Z

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.