© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 19813 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
19813

INDEX

Explanations

literal

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

-de

-0.07

／/

-0.06

های

-0.06

mdp

-0.06

-0.06

 усе

-0.06

 Sheila

-0.06

.pl

-0.06

gon

-0.06

いて

-0.06

POSITIVE LOGITS

 literal

0.08

objective

0.06

vote

0.06

Ein

0.06

 Extreme

0.06

.MediaType

0.06

LEV

0.06

 collectionView

0.06

 پست

0.06

izards

0.06

Activations Density 0.005%

No Known Activations