© 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 · 35880 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
35880

INDEX

Explanations

1

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

 Redux

-0.08

anguages

-0.07

िकट

-0.07

 çek

-0.06

(...

-0.06

 Gordon

-0.06

 Chore

-0.06

NoArgsConstructor

-0.06

струмент

-0.06

。这

-0.06

POSITIVE LOGITS

0.07

opl

0.06

 argue

0.06

リーズ

0.06

 inspector

0.06

yz

0.06

ài

0.06

__)↵↵

0.06

ieties

0.06

těž

0.06

Activations Density 0.002%

No Known Activations