

OpenInterpretability
Open-source toolkit to audit what your LLM knows
什麼是 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.
截圖
?
還沒有評論,來搶沙發吧!
X 上關於 OpenInterpretability 的真實討論
去 X 發文


