© 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 · 15-RESID-POST-AA · 25748 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
25748

INDEX

Explanations

code

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

 culo

-0.07

Pdf

-0.07

Jump

-0.06

 propiedad

-0.06

 inmate

-0.06

VEN

-0.06

capt

-0.06

وتر

-0.06

คณะ

-0.06

 آرام

-0.06

POSITIVE LOGITS

liste

0.07

 unreasonable

0.06

()"↵

0.06

izr

0.06

Υ

0.06

 compromises

0.06

 Nearby

0.06

 необ

0.06

_cred

0.06

ierarchical

0.06

Activations Density 0.064%

No Known Activations