---
title: "Neel Nanda — papers of 2024 — 3 papers, the most cited first"
description: "Neel Nanda — papers of 2024: 3 papers on Elamur Research, the most cited first — what each work is about in our own words."
canonical: "https://research.elamur.ai/free/en/authors/neel-nanda/year/2024/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/neel-nanda/year/2024/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Neel Nanda](https://md.research.elamur.ai/free/en/authors/neel-nanda/) / 2024

# Neel Nanda — papers of 2024 — 3 papers, the most cited first

3 papers · [all years of Neel Nanda](https://md.research.elamur.ai/free/en/authors/neel-nanda/#years)

- [Refusal in Language Models Is Mediated by a Single Direction arXiv:2406.11717](https://md.research.elamur.ai/free/en/papers/arditi-2024-refusal-language-models-mediated-single/) — Andy Arditi, Oscar Obeso, Aaquib Syed, et al. · 2024 · 196 citations
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 arXiv:2408.05147](https://md.research.elamur.ai/free/en/papers/lieberum-2024-gemma-scope-open-sparse-autoencoders/) — Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, et al. · 2024 · 115 citations
- [Improving Dictionary Learning with Gated Sparse Autoencoders arXiv:2404.16014](https://md.research.elamur.ai/free/en/papers/rajamanoharan-2024-improving-dictionary-learning-gated-sparse/) — Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, et al. · 2024 · 42 citations