© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

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

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 78872 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
78872

INDEX

Explanations

the

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

ox

-0.07

書

-0.07

ाय

-0.07

対

-0.06

-tier

-0.06

 tutto

-0.06

uvo

-0.06

민

-0.06

_OBJ

-0.06

�

-0.06

POSITIVE LOGITS

bz

0.07

','=','

0.06

fz

0.06

 entertained

0.06

 dưới

0.06

 Melbourne

0.06

<D

0.06

 defaultCenter

0.06

vX

0.06

_altern

0.06

Activations Density 0.050%

No Known Activations