21st May 2024 - Link Blog
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.
Recent articles
- Writing about Agentic Engineering Patterns - 23rd February 2026
- Adding TILs, releases, museums, tools and research to my blog - 20th February 2026
- Two new Showboat tools: Chartroom and datasette-showboat - 17th February 2026