Amplitude-Only FFN Intervention for Tool-Structured LLM Inference: Method, Gated Evaluation Protocol, and Cross-Model Empirical Results
An inference-time intervention that masks feed-forward network activation coordinates while keeping pretrained weights fixed provides a task-dependent intervention surface, with causal mechanisms, equal-budget advantages, repeated-run uncertainty, and serving cost still open.
Sheng Xu, Zhen Chen, Jun-Hua Wang et al.
· 0 citations