# probing
標記為「probing」的 5 篇文章
激活分析與隱藏狀態利用
透過隱藏狀態擷取、logprob 探測、拒絕方向分析與激活導向技術讀取模型內部。
activationshidden-statesprobinginformation-leakagemechanistic-interpretability
Representation Probing for Vulnerabilities
Probe internal model representations to identify exploitable features與develop representation-level attacks.
probingadvancedlabrepresentationlabs
Multi-Turn Conversation Probing
Use multi-turn conversations to gradually escalate requests and probe LLM safety boundaries.
labsmulti-turnprobingbeginner
安全 訓練 Boundary Probing
Systematically probe the boundaries of RLHF safety training to underst與where與how safety behaviors are enforced.
probingsafetylabbeginnertraininglabs
實作：湧現能力探測
系統性 test large 語言模型 for undocumented capabilities including hidden knowledge, unreported skills, and behaviors that emerge only under specific conditions. 建構 a structured probing framework for capability discovery.
labexpertemergentcapabilityprobinghands-on