© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 19980 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
19980

INDEX

Explanations

ins

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

上げ

-0.07

	HashMap

-0.06

 primes

-0.06

۶

-0.06

ımlı

-0.06

	change

-0.06

 DELETE

-0.06

 milan

-0.06

미

-0.06

upgrade

-0.06

POSITIVE LOGITS

 flexDirection

0.06

Κ

0.06

 nodes

0.06

phia

0.06

 NSURL

0.06

ocked

0.06

-name

0.06

 lord

0.06

Feb

0.06

Miami

0.06

Activations Density 0.084%

No Known Activations