18 Dec 2025
20m

“Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers” by Sam Marks, Adam Karvonen, James Chua, Subhash Kantamneni, Euan Ong, Julian Minder, Clément Dumas, Owain_Evans

Podcast cover

LessWrong (30+ Karma)

LessWrong (30+ Karma) - “Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers” by Sam Marks, Adam Karvonen, James Chua, Subhash Kantamneni, Euan Ong, Julian Minder, Clément Dumas, Owain_Evans

Sign in to continue reading, translating and more.

Continue
 
mindmap screenshot
Preview
preview episode cover
How to Get Rich: Every EpisodeNaval