© 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 · 9683 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
9683

INDEX

Explanations

text

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

-el

-0.07

股份

-0.07

.removeClass

-0.06

ldb

-0.06

edeki

-0.06

Environment

-0.06

 conflic

-0.06

.sendFile

-0.06

 harbor

-0.06

Producto

-0.06

POSITIVE LOGITS

crc

0.07

(contents

0.07

に向

0.06

 تص

0.06

 blends

0.06

 moist

0.06

Vers

0.06

HEET

0.06

0.06

 quant

0.06

Activations Density 0.001%

No Known Activations