© 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 · 22741 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
22741

INDEX

Explanations

target of "for"

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

ê°ģ

-0.11

ÙĬÙĪÙĨ

-0.10

¶Į

-0.09

ç©º

-0.09

 jeder

-0.09

ÙĨØ¯Ø§

-0.09

etch

-0.09

-0.09

elpers

-0.09

ees

-0.09

POSITIVE LOGITS

 reasons

0.21

 instance

0.21

 sure

0.18

/of

0.17

king

0.17

 example

0.17

ges

0.16

 both

0.16

aging

0.16

ays

0.14

Activations Density 0.098%

No Known Activations