[KongchangAI]
Unverified50% confidenceFactExact time

Anthropic在2023年发表的研究表明,通过SAE可以从Claude模型中提取出对应'金门大桥'、'代码错误'等具体概念的单元特征

1
Sources
50%
Confidence
Long-term
Relevance
8/13/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/742334
API
curl https://kongchang.com/api/v1/knowledge/claims/742334
MCP
get_claim(id=742334)