HugMap
人工智能
云计算
半导体
网络安全
企业软件
区块链
量子计算
生物科技
新能源与智能制造
智能穿戴
机器人
智能手机
图谱探索
趋势分析
登录
注册
activation patching
技术
0
衍生技术
0
相关产品
0
相关事件
关系图谱
概览
衍生技术
相关论文
相关专利
相关产品
相关事件
相关文章
activation patching · 相关文章
相关文章
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
ArXiv CS.CL
2026-08-14
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
ArXiv CS.AI
2026-08-10
Test, then Route: How Language Models Execute In-Context Conditional Rules Across Models and Languages
ArXiv CS.CL
2026-08-06
Cross-Layer Interaction under Weight-Space Ablation: A Closed-Form Attention Jacobian Bound and a Test on a Real Pretrained Model
ArXiv CS.AI
2026-08-05
A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation
ArXiv CS.AI
2026-08-05
Divergent large language model predictions from convergent representations in ambiguous word pairs
ArXiv CS.CL
2026-08-04
Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
ArXiv CS.CL
2026-08-04
Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs
ArXiv CS.CL
2026-07-21
Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models
ArXiv CS.CL
2026-07-21
Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models
ArXiv CS.CL
2026-07-21