© 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

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 32125 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
32125

INDEX

Explanations

is often used

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf

Configuration

Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ORK

-0.09

orks

-0.09

ESH

-0.09

 Preferred

-0.08

-0.08

aily

-0.08

-0.08

cht

-0.08

-0.08

/stdc

-0.08

POSITIVE LOGITS

 sometimes

0.18

 often

0.17

 usually

0.14

sometimes

0.13

NOT

0.12

 believed

0.12

 Sometimes

0.12

 Often

0.12

 fairly

0.12

 similar

0.12

Activations Density 0.172%

No Known Activations