© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 77510 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77510

INDEX

Explanations

Pokémon

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_BYTE

-0.07

dess

-0.07

ritch

-0.07

 استان

-0.06

Hed

-0.06

acias

-0.06

oogle

-0.06

EF

-0.06

elic

-0.06

 estado

-0.06

POSITIVE LOGITS

quirer

0.06

้ง

0.06

coach

0.06

)++;↵

0.06

notin

0.06

']);

0.06

-layout

0.06

YM

0.06

垂

0.06

}>
↵

0.06

Activations Density 0.013%

No Known Activations