2026. On the non-identifiability of steering vectors in large language models

Similar preprints — Semantic Scholar

Cited by (2)

• 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

• Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

  Harness-updating capability is essentially flat across model capability tiers, while harness-benefit is non-monotonic — a decoupling with direct implications for how capability budgets should be alloc