© 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 · 120909 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
120909

INDEX

Explanations

-us

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

verter

-0.07

广

-0.07

emin

-0.07

 LiveData

-0.06

agnetic

-0.06

 Арх

-0.06

Electronic

-0.06

hexdigest

-0.06

кт

-0.06

Paid

-0.06

POSITIVE LOGITS

 může

0.07

 Franz

0.06

<context

0.06

-us

0.06

 validationResult

0.06

複

0.06

=:

0.06

ooks

0.06

 نزدیک

0.06

Usu

0.06

Activations Density 0.002%

No Known Activations