© 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 · 4548 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
4548

INDEX

Explanations

.body

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

(training

-0.07

 SignIn

-0.07

-0.07

něl

-0.07

variant

-0.06

 Newsletter

-0.06

 bryster

-0.06

 oppon

-0.06

-0.06

ópez

-0.06

POSITIVE LOGITS

.documentElement

0.09

.MM

0.06

_DM

0.06

ি�

0.06

genes

0.06

φή

0.06

 Edited

0.06

AUT

0.06

0.06

 corpse

0.06

Activations Density 0.001%

No Known Activations