1
High-Dimensional Random Projection for Activation Steering in Language Models
用高维随机投影巧妙引导语言模型激活，无需额外训练即可调控模型行为，为模型可解释性提供新思路。
arXiv:2606.15092v1 Announce Type: new Abstract: Activation steering has emerged as a key methodology for controlling the behavior of large language mo…