© 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 · 22991 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
22991

INDEX

Explanations

code snippets

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

 rests

-0.07

 dicho

-0.07

ΜΑ

-0.07

 Craw

-0.07

zeitig

-0.07

 Banco

-0.07

 volcan

-0.07

.have

-0.06

 vrch

-0.06

ypy

-0.06

POSITIVE LOGITS

;-

0.07

 **↵

0.06

 jiné

0.06

#↵

0.06

 weird

0.06

 liners

0.06

 Greece

0.06

 densities

0.06

 legend

0.06

□

0.06

Activations Density 0.000%

No Known Activations