© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 38540 ｜ Neuronpedia

Home
Llama3.3-70B-IT (Instruct)
50-RESID-POST-GF
38540

INDEX

Explanations

is that correct/what

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

otty

-0.11

quer

-0.10

cer

-0.10

æīį

-0.10

 PERF

-0.10

 Perfect

-0.09

 perfectly

-0.09

Ãªt

-0.09

ulis

-0.09

ishi

-0.09

POSITIVE LOGITS

 correct

0.13

 what

0.13

 Correct

0.11

çŀ

0.10

what

0.10

 possible

0.10

 true

0.10

alama

0.10

Correct

0.09

correct

0.09

Activations Density 0.028%

No Known Activations