OpenInterpretability
Open-source toolkit to audit what your LLM knows
什么是 OpenInterpretability？
The first mech interp toolkit that runs inside Claude Code, Cursor, and Cline via MCP. Production probes (FabricationGuard, agent-probe-guard) catch hallucinations + agent failures. ProbeBench leaderboard, SAE training from 30-min free Colab to paper-grade. Apache-2.0.
截图
?
还没有评论，来抢沙发吧！
X 上关于 OpenInterpretability 的真实讨论
去 X 发帖