© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B · 17-LLAMASCOPE-RES-131K · 105815 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
105815

INDEX

Explanations

instances of the word "this"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elman

-0.07

-,

-0.07

elib

-0.07

piar

-0.06

Ä°T

-0.06

Ø²

-0.06

tran

-0.06

hub

-0.06

oleon

-0.06

icom

-0.06

POSITIVE LOGITS

erus

0.08

 Saunders

0.08

 then

0.07

ahlen

0.07

 Singleton

0.07

 done

0.07

fact

0.07

/mat

0.06

ahn

0.06

aldo

0.06

Activations Density 0.039%

No Known Activations