© 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 · 15-RESID-POST-AA · 75467 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
75467

INDEX

Explanations

Industrial hoppers

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

จ

-0.07

 presenta

-0.07

ंगठन

-0.07

 mostra

-0.06

tj

-0.06

 Samar

-0.06

zo

-0.06

ject

-0.06

대표

-0.06

 descr

-0.06

POSITIVE LOGITS

hop

0.11

Hop

0.09

Hop

0.09

 hops

0.09

-hop

0.08

 Hopkins

0.08

.Singleton

0.07

 Splash

0.07

 марш

0.07

HTTPRequestOperation

0.07

Activations Density 0.004%

No Known Activations