© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 92781 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
92781

INDEX

Explanations

ET

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

_scan

-0.08

itchens

-0.07

िह

-0.07

ünde

-0.06

 인터

-0.06

[axis

-0.06

_COUNT

-0.06

 />;↵

-0.06

 ㅋㅋ

-0.06

_malloc

-0.06

POSITIVE LOGITS

ぅ

0.06

 ilişk

0.06

/wiki

0.06

 Phrase

0.06

 रस

0.06

()}

0.06

Hos

0.06

 Strength

0.06

 kond

0.06

 panda

0.06

Activations Density 0.013%

No Known Activations