mlp-neurons

Tag

Cards List
#mlp-neurons

Output Vector Editing for Memorization Mitigation in Large Language Models

arXiv cs.CL · 2026-06-18 Cached

Presents output vector editing, a constrained-optimization weight edit to mitigate memorization in LLMs by modifying MLP neuron output vectors instead of zeroing activations, achieving up to 87.9% suppression with minimal locality failures.

0 favorites 0 likes
#mlp-neurons

Can Editing 1 Neuron Fix Repetition Loops in LLMs?

arXiv cs.LG · 2026-06-15 Cached

This paper investigates whether repetition loops in long factual enumeration tasks by Gemma 4 models can be fixed by editing a single neuron. It finds that targeted weight edits on a small set of MLP neurons can significantly reduce loop failures, though not completely eliminate doom looping in larger models.

0 favorites 0 likes
#mlp-neurons

Targeted Neuron Modulation via Contrastive Pair Search

Hugging Face Daily Papers · 2026-05-12 Cached

Contrastive neuron attribution (CNA) identifies a sparse set of MLP neurons that distinguish harmful from benign prompts, enabling effective behavioral steering in instruction-tuned LLMs without degrading output quality. The method reduces refusal rates by over 50% on jailbreak benchmarks while preserving fluency.

0 favorites 0 likes
← Back to home

Submit Feedback