© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

LLAMA3.1-8B-IT · 27-RESID-POST-AA · 10246 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
10246

INDEX

Explanations

par

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

link

-0.07

_invoice

-0.07

альная

-0.06

.norm

-0.06

روع

-0.06

ories

-0.06

description

-0.06

 civilian

-0.06

 substitution

-0.06

ิ้

-0.06

POSITIVE LOGITS

 puppies

0.07

지

0.07

 help

0.06

&B

0.06

0.06

 Đầu

0.06

\Action

0.06

 Appropri

0.06

 companions

0.06

 Bust

0.06

Activations Density 0.001%

No Known Activations