Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Distributed Sparse Interventions in Language Models

cs.LG · 2026-07-08 · conditional · novelty 6.0

Sparse interventions on 8–64 neurons distributed across layers can activate task behavior in instruction-tuned LLMs, outperforming first-order linear steering approaches by modeling nonlinear neuron interactions.

citing papers explorer

Showing 1 of 1 citing paper.

  • Distributed Sparse Interventions in Language Models cs.LG · 2026-07-08 · conditional · none · ref 13

    Sparse interventions on 8–64 neurons distributed across layers can activate task behavior in instruction-tuned LLMs, outperforming first-order linear steering approaches by modeling nonlinear neuron interactions.