© 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 · 19-RESID-POST-AA · 35593 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
35593

INDEX

Explanations

.junit

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

Assertion

-0.07

 trace

-0.06

 authentication

-0.06

,array

-0.06

 Race

-0.06

-0.06

submission

-0.06

-0.06

 race

-0.06

Coverage

-0.06

POSITIVE LOGITS

glm

0.07

津

0.07

ButtonTitles

0.07

MenuBar

0.07

GLuint

0.07

 jamais

0.07

稍

0.07

 навч

0.07

发

0.06

به

0.06

Activations Density 0.001%

No Known Activations