Unverified50% confidenceFactExact time
Anthropic published a paper in 2024 demonstrating how to locate neuron groups related to concepts such as 'honesty' and 'harm recognition' in the Claude model, and how intervening in these neurons can alter model behavior.
1
Sources
50%
Confidence
Long-term
Relevance
9/10/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAnthropic published mechanistic interpretability research on the internal feature interpretation of Claude in 2024, discovering millions of interpretable feature units.75% similarUnverifiedIn a paper published by Anthropic in 2023, sparse autoencoders were used to find tens of thousands of interpretable features in Claude, including emotional states and programming language types.73% similarUnverifiedAnthropic发布了Model Spec文档，详细规定了Claude在面对不确定性时的行为准则68% similarUnverifiedAnthropic has released Claude Science, an application built specifically for scientific research, which is currently in beta.68% similarUnverifiedAnthropic曾于2023年公开Claude在claude.ai上使用的完整系统提示，供用户和研究者审计68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/886064API
curl https://kongchang.com/api/v1/knowledge/claims/886064MCP
get_claim(id=886064)