Simon Willison’s Weblog

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet (via) Big advances in the field of LLM interpretability from Anthropic, who managed to extract millions of understandable features from their production Claude 3 Sonnet model (the mid-point between the inexpensive Haiku and the GPT-4-class Opus).

Some delightful snippets in here such as this one:

We also find a variety of features related to sycophancy, such as an empathy / “yeah, me too” feature 34M/19922975, a sycophantic praise feature 1M/847723, and a sarcastic praise feature 34M/19415708.