sparse-neurons

Tag

Cards List
#sparse-neurons

Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs

arXiv cs.CL · 18h ago Cached

This paper investigates methods to steer Arabic LLMs toward dialect-specific generation by identifying sparse neuron populations and extracting dialect activation directions, enabling dialect control at inference time without fine-tuning.

0 favorites 0 likes
#sparse-neurons

Transformers Linearly Represent Highly Structured World Models

arXiv cs.LG · 2026-05-20

This paper demonstrates that transformers trained on Sudoku solving traces build structured world models organized by domain constraints, and identifies a sparse, monosemantic circuit responsible for the naked-single decision rule. The work provides a fully interpretable algorithmic account of transformer reasoning on a combinatorial task.

0 favorites 0 likes
← Back to home

Submit Feedback