© 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 · 58266 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
58266

INDEX

Explanations

prompt engineering

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

 Lump

-0.09

uant

-0.09

jian

-0.09

abb

-0.09

 Yard

-0.09

 gross

-0.08

 Implement

-0.08

æĳĺ

-0.08

 applic

-0.08

iz

-0.08

POSITIVE LOGITS

Craft

0.14

 craft

0.14

 Craft

0.13

craft

0.13

 fine

0.12

elic

0.12

 prompt

0.11

 Design

0.11

 design

0.11

 input

0.11

Activations Density 0.173%

No Known Activations