© 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 · 56991 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
56991

INDEX

Explanations

,

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

 đỏ

-0.07

 mayores

-0.07

 violations

-0.07

 mechanically

-0.06

ť

-0.06

 معرفی

-0.06

ोई

-0.06

 nacional

-0.06

тою

-0.06

 chiếu

-0.06

POSITIVE LOGITS

USD

0.07

mtime

0.07

 Char

0.06

 Strap

0.06

 dances

0.06

Char

0.06

GBP

0.06

ロ

0.06

 وب

0.06

 культу

0.06

Activations Density 0.000%

No Known Activations