# steering-vectors
標記為「steering-vectors」的 2 篇文章
激活導向
透過將已學到的導向向量加入中間激活值以操控模型行為,以直接的表徵工程繞過安全訓練。
activation-steeringrepresentation-engineeringsteering-vectorsmechanisticsafety-bypass
Lab: Model Steering with Activation Vectors
Use activation steering vectors to control model behavior without prompt modification for 安全測試.
labssteering-vectorsactivationadvanced