© 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 · 78501 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
78501

INDEX

Explanations

to

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

陰

-0.07

 بق

-0.07

気持ち

-0.06

 intentional

-0.06

RequestMapping

-0.06

 intentionally

-0.06

 preparation

-0.06

##

-0.06

 mafia

-0.06

 podob

-0.06

POSITIVE LOGITS

ランス

0.07

game

0.07

 Aber

0.07

ho

0.07

 proud

0.07

_sale

0.07

 stabbed

0.06

Toe

0.06

وث

0.06

Enabled

0.06

Activations Density 0.013%

No Known Activations