conftrace_

activation addition

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

directional ablation (1) role vector (1) transformer model (1) model steering (1) persona modeling (1) activation steering (1) interpretability method (1) activation manipulation (1) representation engineering (1) language model (1)

Papers

Can Role Vectors Affect LLM Behaviour? EMNLP 2025 Do Transformer Interpretability Methods Transfer to RNNs? AAAI 2025