© 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 · 11-RESID-POST-AA · 52143 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
52143

INDEX

Explanations

to

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

曰

-0.07

 markings

-0.07

那里

-0.06

لو

-0.06

 شده

-0.06

akes

-0.06

("<

-0.06

-0.06

-mark

-0.06

μορ

-0.06

POSITIVE LOGITS

 related

0.07

sex

0.06

生物

0.06

 Fibonacci

0.06

_system

0.06

tem

0.06

 temas

0.06

 Lös

0.06

 Plantae

0.06

함

0.06

Activations Density 0.037%

No Known Activations