© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 36279 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
36279

INDEX

Explanations

circular

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

وو

-0.07

利

-0.07

Jer

-0.07

	fire

-0.06

같

-0.06

�

-0.06

 teklif

-0.06

Gran

-0.06

 Deng

-0.06

TOT

-0.06

POSITIVE LOGITS

 hopeful

0.06

acles

0.06

ersive

0.06

 RootState

0.06

wers

0.06

onomies

0.06

ν

0.06

 Accessed

0.06

 principals

0.06

 corrupted

0.06

Activations Density 0.003%

No Known Activations