© 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 · 101949 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
101949

INDEX

Explanations

Logo images

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

 configFile

-0.07

 ROCK

-0.06

那里

-0.06

 Rock

-0.06

 entfer

-0.06

nag

-0.06

 destroying

-0.06

 ");↵

-0.06

�

-0.06

=r

-0.06

POSITIVE LOGITS

ụy

0.06

 Nottingham

0.06

ved

0.06

サー

0.06

allback

0.06

achine

0.06

 UIAlertAction

0.06

 пара

0.06

fastcall

0.06

ono

0.06

Activations Density 0.000%

No Known Activations