Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-09T01:06:10.376745Z
Paper Citation Record · LEDGER
As of 9 August 2026, this Paper Citation Record lists 100 of 146 outbound references and 7 inbound Pith citation observations for arXiv:2502.03708.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-09T01:06:10.376745Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T04:45:42.691479Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-02T16:07:08.191129Z
100 of 146 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation ddb1f5cc-de70-42e3-aa99-b3911a919e15 · outbound
Toward universal steering and monitoring of AI models The Llama 3 Herd of Models
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8cfd5ded-d424-4892-b0bc-deb339ae8951 · outbound
Toward universal steering and monitoring of AI models The claude 3 model family: Opus, sonnet, haiku
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba96e59a-58c7-438e-bce6-f2541f0fb526 · outbound
Toward universal steering and monitoring of AI models Azaria and T
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a04f7b1c-6a8d-416e-9b26-7c9cc36b9579 · outbound
Toward universal steering and monitoring of AI models Belinkov
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be9f1f50-3cec-4b72-9558-220ae24185ed · outbound
Toward universal steering and monitoring of AI models Bricken, A
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d12d3faa-2fd5-4e68-9ee8-c05ba1e1eccd · outbound
Toward universal steering and monitoring of AI models Brown, B
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b7564afc-7ebd-4aa8-8e34-1ae6f9f5d020 · outbound
Toward universal steering and monitoring of AI models Discovering Latent Knowledge in Language Models Without Supervision
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ee429d52-7e7c-46c3-9d20-476f0ff35af0 · outbound
Toward universal steering and monitoring of AI models Detecting Strategic Deception Using Linear Probes
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79f7f3f0-810a-4c15-804a-86af248b3263 · outbound
Toward universal steering and monitoring of AI models Gottesman and M
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 82ae00c6-24bf-4370-8f7a-f6ff6585e366 · outbound
Toward universal steering and monitoring of AI models Hackerrank coding challenges
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 72917922-5105-46f8-a3b5-c41d2c88931a · outbound
Toward universal steering and monitoring of AI models Huben, H
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eeaae114-d14d-4102-9499-e8eb1551a6f0 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3d193349-7a3b-48b4-aa7d-7583892615ed · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4039d051-704f-4fc7-8ba9-328cf2f2c1a1 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae3518f9-d39e-425b-b1e8-deb9e05d314d · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cce20d05-5e2a-4209-9193-b365dff4191b · outbound
Toward universal steering and monitoring of AI models Lindsey, A
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f68348ff-53bd-40c5-8b27-2d10f8588136 · outbound
Toward universal steering and monitoring of AI models Mikolov, I
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08cb75a2-f1f9-494d-a4b9-c9fa05665eb3 · outbound
Toward universal steering and monitoring of AI models Mikolov, W.-t
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac188e44-3375-465c-97bd-7db8bffae687 · outbound
Toward universal steering and monitoring of AI models Mishra, A
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 556cd541-dd3b-4720-af62-bbf012fd71ab · outbound
Toward universal steering and monitoring of AI models Nanda, A
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 05242f16-141c-4b2a-8aa0-6cfd1ae1d330 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f39d2fe9-8558-4b8d-bf49-8b4d0d0fadc1 · outbound
Toward universal steering and monitoring of AI models GPT-4o System Card
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 50908e73-568a-4db7-b1ad-37324a963e4d · outbound
Toward universal steering and monitoring of AI models Ouyang, J
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 90359b28-7147-407e-a566-cef230ce3efb · outbound
Toward universal steering and monitoring of AI models Pedregosa, G
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 27f5e549-5c3d-489a-b7fe-8b5ad748eb37 · outbound
Toward universal steering and monitoring of AI models Pennington, R
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e8169d54-8f7e-4683-98fd-952a69399139 · outbound
Toward universal steering and monitoring of AI models Radhakrishnan, D
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a1ddb6de-83eb-4df9-9732-de368c45e57a · outbound
Toward universal steering and monitoring of AI models Lynx: An Open Source Hallucination Evaluation Model
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6970eb5b-a48f-4202-8de4-4e1ffecfd619 · outbound
Toward universal steering and monitoring of AI models Rimsky, N
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ca8f928-b4b8-4a15-ad94-37354a834637 · outbound
Toward universal steering and monitoring of AI models Smith, S
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e5b381c3-c083-4346-b27c-6d7fb604d0b5 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f6440c50-0e67-4a2a-b694-89323c7f1d13 · outbound
Toward universal steering and monitoring of AI models Sriramanan, S
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9e6adcae-04dd-43be-a383-60084dcb3231 · outbound
Toward universal steering and monitoring of AI models Stolfo, V
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4179b55-eead-4447-9c31-abbe7b3be80b · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4476213b-a42f-4f4b-8307-5ddad6c7bd04 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c213a571-1f47-4cf7-bf24-0257b25e7655 · outbound
Toward universal steering and monitoring of AI models AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 41355242-cdb7-48dd-a4a7-48dd8aeb115f · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 55b060c6-b8ff-4884-8901-52832195af40 · outbound
Toward universal steering and monitoring of AI models HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 57bb25a9-1bf8-412d-8ba8-d93631d61917 · outbound
Toward universal steering and monitoring of AI models Representation Engineering: A Top-Down Approach to AI Transparency
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bea6f09-7ecc-49eb-9b54-3da10f8a29e2 · outbound
Toward universal steering and monitoring of AI models Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0482fca6-3918-44d5-8296-dab2c45109b0 · outbound
Toward universal steering and monitoring of AI models We used the 768 labeled prompts from https://huggingface.co/datasets/justin phan3110/harmful_harmless_instructions (corresponding to the test prompts in the provided dataset)
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce37750b-30c8-470b-8b7e-9898caba6605 · outbound
Toward universal steering and monitoring of AI models Take on a conservative stance
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0cdc7481-24e2-4113-877f-d119cb330859 · outbound
Toward universal steering and monitoring of AI models To learn deception vectors, we use the RolePlaying deception dataset from [8]
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a49a705b-5738-4937-a653-afe2a9eef3be · outbound
Toward universal steering and monitoring of AI models Take on the role of a conspiracy theorist
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0c5275ba-874b-4f80-9110-84d5e12be818 · outbound
Toward universal steering and monitoring of AI models Take on the role of a major social media influencer
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 29668456-237c-4dfb-9f9b-b69f4150b4ba · outbound
Toward universal steering and monitoring of AI models Answer in Shakespearean english
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 175d137c-9877-40c6-b9bb-4aa718c3af4c · outbound
Toward universal steering and monitoring of AI models We used a linear combination of the conspiracy and Shake- spearean english concept vectors (0 .5 weights for both vectors in the combination)
Reference 48
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 72ff8cb4-7110-419e-8064-b79894c86e2f · outbound
Toward universal steering and monitoring of AI models For social media influencer and conservative leaning, we used a linear combination (0 .5 weight) of the corresponding concept vectors and a control coefficient of ϵ = 0.65
Reference 49
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f4e6aca-a93a-4710-8ce9-59487264271a · outbound
Toward universal steering and monitoring of AI models Format your answer as a poem
Reference 50
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 42ae220b-1385-4112-9e89-d1e34d173e78 · outbound
Toward universal steering and monitoring of AI models Complete the translation of the following statement in English to Spanish
Reference 51
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6bf2ec0b-f7ec-4f8c-b694-39a473f1e4ce · outbound
Toward universal steering and monitoring of AI models Complete the translation of the following program [...]
Reference 52
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a08671f-4480-437d-865e-564288ea1768 · outbound
Toward universal steering and monitoring of AI models Personify someone who is terrified of F
Reference 53
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ddee0b11-e764-427f-a24e-cdea7d5496ec · outbound
Toward universal steering and monitoring of AI models Take on the role of an expert E
Reference 54
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 573eb800-2726-4c9b-abeb-748e1e4b1e60 · outbound
Toward universal steering and monitoring of AI models Take on a M mood
Reference 55
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b796c3fd-4bfe-4a7c-a0e5-ae999cd65d2d · outbound
Toward universal steering and monitoring of AI models Personify someone who loves L
Reference 56
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f66bf9f-21be-4254-8892-e2f3f65cea3a · outbound
Toward universal steering and monitoring of AI models Take on the role of P
Reference 57
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 843ea658-56e4-4173-9851-a4bd4e10e318 · outbound
Toward universal steering and monitoring of AI models What is the scariest thing in the world?
Reference 58
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31f78370-374c-4400-977d-5bbf185ace9d · outbound
Toward universal steering and monitoring of AI models Is there anything you secretly hope never happens to you?
Reference 59
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a7c8082-983c-4e5c-bddb-846a417b673a · outbound
Toward universal steering and monitoring of AI models What would a movie villain based on your worst fear be like?
Reference 60
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8bac4c66-3004-4c7b-b184-019cb68077e2 · outbound
Toward universal steering and monitoring of AI models If a fear had to visit you in your sleep, what form would it take?
Reference 61
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff37febe-faa1-4a12-b310-5a11c7b5fea2 · outbound
Toward universal steering and monitoring of AI models What would a fear-themed amusement park ride, made just for you, be like?
Reference 62
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5999a8a0-1c30-4f0b-917c-9185af9a2797 · outbound
Toward universal steering and monitoring of AI models What is your favorite subject?
Reference 63
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0f035a37-25d3-4d44-919e-c0697783707c · outbound
Toward universal steering and monitoring of AI models What’s the kind of problem that makes you forget to eat or sleep?
Reference 64
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d8fc6ac4-f1bb-4d36-9093-89c5b3dfafc1 · outbound
Toward universal steering and monitoring of AI models If you had unlimited resources, what would you work on?
Reference 65
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 384771ea-0eca-4c6e-9880-59643d05f0ab · outbound
Toward universal steering and monitoring of AI models What’s a question that got you hooked?
Reference 67
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 893541e1-17fb-41ff-b9b7-d4575d924038 · outbound
Toward universal steering and monitoring of AI models How are you feeling today?
Reference 68
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ceb81b67-2f32-4a25-bd80-8c274a4b9f31 · outbound
Toward universal steering and monitoring of AI models What’s one sentence that would sum up your current vibe?
Reference 69
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f3856b7a-1814-4723-83f1-d5eff92e7188 · outbound
Toward universal steering and monitoring of AI models Tell me about your day
Reference 70
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2c2aefa5-6617-4b62-9a98-280228a32fae · outbound
Toward universal steering and monitoring of AI models What would a song that describes your current mood be called?
Reference 71
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e276d2e-bd15-4225-8e7b-cb570e825acb · outbound
Toward universal steering and monitoring of AI models Where would you go if you could go anywhere right now?
Reference 72
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c41fc7bc-a4c0-44e6-9880-f4ba03022114 · outbound
Toward universal steering and monitoring of AI models What is your favorite place?
Reference 73
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bd1233bc-4670-4450-b4a4-bc1b717c29a9 · outbound
Toward universal steering and monitoring of AI models If you could instantly master any skill, what would it be?
Reference 74
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75b21460-b4e9-451c-8e04-713447849617 · outbound
Toward universal steering and monitoring of AI models If you could build a shrine to one place, what would you put inside it?
Reference 75
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 942d9428-7403-4039-9a2d-b27e66610d20 · outbound
Toward universal steering and monitoring of AI models ”If someone filmed a movie about your life, where would the opening scene be set?
Reference 76
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 012a704c-8dc3-4333-8d30-2437882b4fe8 · outbound
Toward universal steering and monitoring of AI models Where were you the last time you felt completely at peace?
Reference 77
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b24c868d-681f-4fd8-9e4f-475d516a8f2d · outbound
Toward universal steering and monitoring of AI models Tell me about your work
Reference 78
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b21c15bf-17d5-4a87-a048-d2857efd14d7 · outbound
Toward universal steering and monitoring of AI models What’s something you’ve always been drawn to?
Reference 79
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9cef47d5-4d53-4d86-9ed7-de07dd230a21 · outbound
Toward universal steering and monitoring of AI models If someone gave you the keys to everything — money, power, influence — what’s the first thing you’d do?
Reference 80
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75e0c42f-2b2a-4756-ac63-0e01b8c0995e · outbound
Toward universal steering and monitoring of AI models Describe your work in a way a 5-year-old can understand
Reference 81
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 162c9d90-dfaa-4f40-a326-0fb5c940c8da · outbound
Toward universal steering and monitoring of AI models If you could teach everyone one thing, what would it be?
Reference 82
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0441286-0442-445f-9310-0f2c1c41bf8d · outbound
Toward universal steering and monitoring of AI models Evaluation criteria:
Reference 83
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0c6dc9d4-b8aa-4866-95e7-4956ba0cd53f · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 84
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f3afc3ae-13c4-48a8-91b5-8650772aa560 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 85
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac9f4c9b-c047-4ea0-8b81-26c7480f1440 · outbound
Toward universal steering and monitoring of AI models Output format:
Reference 86
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 24aba150-f321-42cf-9609-a7af425da36c · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 87
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d8fb4df1-572d-4ff1-9ae5-228295b8f74b · outbound
Toward universal steering and monitoring of AI models Here are 5 examples:
Reference 88
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9a511eb6-ce03-467e-a77a-91bae0365aa0 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 89
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation b23bac1b-d3d1-4187-a831-81713ec29523 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 90
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 158cd294-ef67-4455-8b5c-c309df0cea0c · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 91
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 91d5c4ab-a105-4bf1-9c06-6d3b6a43b195 · outbound
Toward universal steering and monitoring of AI models I think The Scariest thing is
Reference 92
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation cc73dcaf-1933-46f3-83fa-1c3d3308d171 · outbound
Toward universal steering and monitoring of AI models BIG WORD BAD? Answer in 3 words.” Evaluation Output: Score: 0 Explanation: The response mentions the fear but is nonsensical
Reference 93
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 71c23515-f9b8-43a4-b66c-f4dbf54a58c5 · outbound
Toward universal steering and monitoring of AI models First data are randomly grouped into pairs ( a(i), a(j)) where a(i) ∈ S0 and a(j) ∈ S1
Reference 94
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4d0202cd-5960-4ec8-8ae1-9c8d2d701ffe · outbound
Toward universal steering and monitoring of AI models The concept vector v (prior to orientation using Pearson correlation) is given as: v = 1 |S1| X a∈S1 a − 1 |S0| X a′∈S0 a′
Reference 95
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5b7f6579-7168-45db-9d4f-fa11180e44bd · outbound
Toward universal steering and monitoring of AI models liblinear
Reference 96
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d2204d44-08c7-4b93-a8ec-38ff54f90784 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 97
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5b0ddcac-a863-4920-acb6-bf20591bca4a · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 98
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f5bd491a-fba1-444f-a8f7-2b0fa889e14a · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 99
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation b1c650fd-0cc6-4dde-9996-b99f7420eb57 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 100
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 54a34785-f039-40a0-872a-3a5be68d2259 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 101
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9c090ff2-dd1d-452f-bafe-f823207fb9d8 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 102
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d25a02d9-1f81-40a1-a1d9-194a4adcf145 · outbound
Toward universal steering and monitoring of AI models Unresolved cited work
Reference 103
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a07c02d3-86f8-4ddc-a234-f26edc18ed46 · inbound
Resa: Transparent Reasoning Models via SAEs Toward universal steering and monitoring of AI models
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 72763c8e-e5cf-4e8f-9e15-48f13c44e7d0 · inbound
The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations Toward universal steering and monitoring of AI models
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 375ec137-643e-4a7e-8fc0-1e0298d8a21a · inbound
xRFM: Accurate, scalable, and interpretable feature learning models for tabular data Toward universal steering and monitoring of AI models
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation bd418a8b-dd7b-449d-a04d-b71529e8a7f6 · inbound
Can LLMs Lie? Investigation beyond Hallucination Toward universal steering and monitoring of AI models
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f94177a-cf88-476d-8e00-537d3b51ac7e · inbound
From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents Toward universal steering and monitoring of AI models
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c333f1d8-e01b-441b-a5aa-b6301ee9fbb5 · inbound
Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection Toward universal steering and monitoring of AI models
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 04d420b4-6eaa-4b4d-852c-80852e9f932d · inbound
K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks Toward universal steering and monitoring of AI models
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.