Can Role Vectors Affect LLM Behaviour?

Similar preprints — Semantic Scholar

Cited by (2)

• Steering at the Source: Style Modulation Heads for Robust Persona Control

  Residual-stream activation steering reliably degrades text coherency when steering vectors push models toward out-of-distribution behavior, and this collapse goes undetected by standard benchmarks: MM

• What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors

  Behavioral defaults in Qwen3-8B (Q8B) and gpt-oss-20b (G20B) track their training norms with systematic fidelity: all nine agentic traits are natural in both models, and clinician defaults align with