GitHub
model-steering
Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified model versions.
☆ 6查看技能
ndif-team AI Skills
GitHub ↗浏览 ndif-team 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
作者统计
已收录技能
6收录技能的仓库 Stars 合计
36仓库 Forks
0平均每个技能的仓库 Stars
6同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
热门分类
近期收录动态
全部技能
GitHub
causal-tracing
Causal mediation analysis to identify which model components mediate specific behaviors. Use when investigating how information flows through the network and which neurons or layers are causally responsible for...
☆ 6查看技能
GitHub
attribution-patching
Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.
☆ 6查看技能
GitHub
activation-patching
Causal intervention via activation patching to identify important model components. Use when determining which layers, heads, or positions are causally responsible for model behavior.
☆ 6查看技能
GitHub
nnsight-basics
Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.
☆ 6查看技能
GitHub
logit-lens
Decode intermediate layer predictions using the Logit Lens technique. Use when analyzing what a model predicts at each layer, understanding information flow, or visualizing layer-wise processing.
☆ 6查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。