Recent Posts

• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
  by smaddoxon 5/22/2024, 2:14:39 PM with 0 comments
• The Matrix: A Bayesian learning model for LLMs
  by smaddoxon 5/3/2024, 5:10:29 PM with 0 comments