Image de couverture de livre

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Templeton, Adly, Conerly, Tom, Marcus, Jonathan, Lindsey, Jack, Bricken, Trenton, Chen, Brian, Pearce, Adam, Citro, Craig, Ameisen, Emmanuel, Jones, Andy, Cunningham, Hoagy, Turner, Nicholas L, McDougall, Callum, MacDiarmid, Monte, Tamkin, Alex, Durmus, Esin, Hume, Tristan, Mosconi, Francesco, Freeman, C. Daniel, Sumers, Theodore R., Rees, Edward, Batson, Joshua, Jermyn, Adam, Carter, Shan, Olah, Chris, Henighan, Tom
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Auditing language models for hidden objectives
par: Marks, Samuel, et autres
Publié: (2025)

When Models Manipulate Manifolds: The Geometry of a Counting Task
par: Gurnee, Wes, et autres
Publié: (2026)

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
par: Jiralerspong, Thomas, et autres
Publié: (2026)

Emotion Concepts and their Function in a Large Language Model
par: Sofroniew, Nicholas, et autres
Publié: (2026)

Scottish meat consumption survey (Feb–Jul 2023): attitudes, COM-B measures, and perceived effectiveness of meat-reduction policies (Best-Worst Scaling)
par: McBey, David, et autres
Publié: (2026)

Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models
par: Szokalski, Adam, et autres
Publié: (2026)

Mao Zedong’s “Talks at the Yan’an Conference on Literature and Art”
par: McDougall, Bonnie S.
Publié: (2020)

The view from within: Professional identity formation when safety events involve trainees
par: Allan McDougall
Publié: (2025)

The psychoanalytic voyage of a breast-cancer patient
par: Joyce McDougall
Publié: (2002)

(Table 5) Age of late Cenozoic sediments of DSDP Hole 68-502A from the Caribbean Sea
par: McDougall, Kristin
Publié: (1996)

Benthic foraminiferal response to the emergence of the Isthmus of Panama and coincident paleoceanographic changes
par: McDougall, Kristin
Publié: (1996)

(Table 4) Relative abundance of benthic foraminifera in late Cenozoic sediments of DSDP Hole 68-503A from the East Pacific Ocean
par: McDougall, Kristin
Publié: (1996)

(Table 5) Age of late Cenozoic sediments of DSDP Hole 68-503A from the East Pacific Ocean
par: McDougall, Kristin
Publié: (1996)

(Table 3) Relative abundance of benthic foraminifera in late Cenozoic sediments of DSDP Hole 68-502A from the Caribbean Sea
par: McDougall, Kristin
Publié: (1996)

(Table 1) Age determination of glass-samples from ODP Hole 135-841B
par: McDougall, Ian
Publié: (1994)

Circumbinary discs for stellar population models
par: Izzard, Robert G., et autres
Publié: (2024)

A Post‐Pandemic Bail System: Lessons Learned From Supervising Accused During Covid‐19
par: Laura MacDiarmid, et autres
Publié: (2025)

Current meter data at station SCM4_10 (CMDB code rcm04051)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_7 (CMDB code rcm04045)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_5 (CMDB code rcm04039)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_3 (CMDB code rcm04033)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_2 (CMDB code rcm04030)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_1 (CMDB code rcm04028)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_9 (CMDB code rcm04050)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_7 (CMDB code rcm54045)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_6 (CMDB code rcm04044)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_4 (CMDB code rcm04036)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_3 (CMDB code rcm04032)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_9 (CMDB code rcm04049)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_5 (CMDB code rcm04040)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_2 (CMDB code rcm04029)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_10 (CMDB code rcm04052)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_7 (CMDB code rcm04047)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_6 (CMDB code rcm04042)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_4 (CMDB code rcm04037)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_3 (CMDB code rcm04031)
par: McDougall, Trevor J
Publié: (2005)

Shipboard acoustic doppler current profiling during cruise 09FA9605 (SAC ID 00467)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_9 (CMDB code rcm04048)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_7 (CMDB code rcm04046)
par: McDougall, Trevor J
Publié: (2005)

Current meter data at station SCM4_6 (CMDB code rcm04041)
par: McDougall, Trevor J
Publié: (2005)