© 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 · 63196 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
63196

INDEX

Explanations

hex byte nibbles

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

 Blair

-0.09

 keyed

-0.09

Mat

-0.09

boss

-0.09

ilha

-0.09

.ReadString

-0.09

Bearer

-0.09

 Barcl

-0.08

 Brut

-0.08

fav

-0.08

POSITIVE LOGITS

 byte

0.17

hex

0.16

byte

0.14

.WriteByte

0.14

0.13

.ReadByte

0.13

hex

0.12

nib

0.12

Hex

0.12

Nib

0.12

Activations Density 0.061%

No Known Activations