© 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 · 55473 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
55473

INDEX

Explanations

,

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

esor

-0.07

_prefs

-0.06

aju

-0.06

_PK

-0.06

bags

-0.06

anza

-0.06

Добав

-0.06

inicio

-0.06

ovky

-0.06

graded

-0.06

POSITIVE LOGITS

كام

0.07

 Czech

0.06

 stake

0.06

 Viện

0.06

 deal

0.06

讯

0.06

#SBATCH

0.06

 nghị

0.06

 Hacker

0.06

~↵↵

0.06

Activations Density 0.012%

No Known Activations