AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 5 of 15 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The swap readout is proposed, which reads each student checkpoint's feature activations on its own, measuring how training changes the student's use of each feature, even for checkpoints unseen by the crosscoder.
It is shown that persistent sycophancy reduction does not guarantee stronger direct refusal, while identifying recovery under user pressure as a distinct, conditional benefit of training intervention.
A family of chunk-level SAEs that encode mean-pooled activations over chunks, each a contiguous span of tokens: Mean-Chunk reconstructs the observed chunk, Cross-Chunk predicts an independently processed neighbor, and Joint-Chunk combines both targets are introduced.
TIDE (Token-level Independent Deficit-Excess correction), which applies bounded Hellinger shaping to suppress the most severe sampled excesses and an analytic teacher top-$K$ injection to restore deficient probability mass without requiring deficit tokens to be sampled, is proposed.
This paper proposesNeighbor Integrated Feature Selection (NIFS), a plug-and-play strategy that leverages representation similarity to improve feature selection for steering and demonstrates consistent performance gains over conventional top-$k$ selection.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.