© 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 · 53701 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
53701

INDEX

Explanations

-C

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

 nữa

-0.08

 Scheduler

-0.07

 Positioned

-0.06

.Pixel

-0.06

 coastline

-0.06

nz

-0.06

POINTS

-0.06

۸

-0.06

ertino

-0.06

await

-0.06

POSITIVE LOGITS

 spices

0.07

ンデ

0.07

.der

0.07

.standard

0.06

.radioButton

0.06

 libertarian

0.06

lsa

0.06

-C

0.06

 коп

0.06

｣

0.06

Activations Density 0.003%

No Known Activations