© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 37549 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
37549

INDEX

Explanations

semicolon

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

飾

-0.06

.avatar

-0.06

ethyst

-0.06

 Gins

-0.06

_foreign

-0.06

雄

-0.06

Zen

-0.06

 justice

-0.06

vc

-0.06

 legion

-0.06

POSITIVE LOGITS

abbix

0.07

 eclips

0.06

Writable

0.06

std

0.06

 تقو

0.06

 ию

0.06

(ChatColor

0.06

-factor

0.06

 chilly

0.06

шли

0.06

Activations Density 0.009%

No Known Activations