© 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 · 16580 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
16580

INDEX

Explanations

dragon and dragoness

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

gan

-0.10

gang

-0.10

brahim

-0.10

 Lump

-0.09

lesen

-0.09

tu

-0.09

lug

-0.09

beros

-0.09

aname

-0.09

avel

-0.09

POSITIVE LOGITS

fly

0.22

flies

0.18

 Slayer

0.14

kin

0.13

fruit

0.12

ess

0.12

Fly

0.11

rid

0.11

fy

0.11

spy

0.11

Activations Density 0.023%

No Known Activations