Mapping the mind of a large language model

linked as “mapping features inside production language models (opens in a new tab)”

linked as “modern language models”

linked as “Mapping the Mind of a Large Language Model”

linked as “mechanistic interpretability”

linked as “research at Anthropic”

linked as “Anthropic for interpretability”

linked as “Mechanistic interpretability research”

linked as ““Golden Gate Bridge” paper”

linked as “Mapping the Mind of a Large Language Model”

linked as “really great contributions”

linked as “most interesting”

linked as “this report”

linked as “though we’re making progress”

linked as “Anthropic’s breakthroughs in mapping and manipulating LLMs”

linked as “Mapping the Mind of a Large Language Model”

linked as “Interpretability”