© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B · 17-LLAMASCOPE-RES-131K · 27551 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
27551

INDEX

Explanations

negative sentiment or criticism

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

ãģıãĤī

-0.08

Ø§

-0.07

anan

-0.07

-looking

-0.07

heed

-0.07

mith

-0.07

 ÙĢ

-0.07

reed

-0.07

eyJ

-0.07

ortion

-0.06

POSITIVE LOGITS

/-

0.11

/+

0.10

webkit

0.09

ÂĢÂ

0.08

jekt

0.07

+-+-

0.07

vs

0.06

.-

0.06

egin

0.06

ãĢĭ

0.06

Activations Density 0.128%

No Known Activations