Anthropic Researchers Map Features in Claude 3 Sonnet
Interesting research from Anthropic. I'm looking forward to reading follow-on work, and I really hope that this will be tested on open source models (like Mistral) to confirm the method.
Syndicated from the fediverse. Read and engage on the original instance.
View original on mander.xyzhttps://transformer-circuits.pub/2024/scaling-monosemanticity/index.htmlOpen linkView original on mander.xyz
1 reply