© 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 · 74232 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
74232

INDEX

Explanations

No Explanations Found

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

allen

-0.08

anton

-0.07

onymous

-0.07

 defaultMessage

-0.07

_mapper

-0.06

VOID

-0.06

fat

-0.06

OLON

-0.06

Fat

-0.06

 Closure

-0.06

POSITIVE LOGITS

getAs

0.06

ukkan

0.06

acct

0.06

gnore

0.06

ugu

0.06

Spo

0.06

peer

0.06

otal

0.06

prep

0.06

0.06

Activations Density 0.000%

No Known Activations

This feature has no known activations.