© 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 · 20750 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
20750

INDEX

Explanations

a

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

.Parameters

-0.07

 security

-0.06

 activism

-0.06

 SECURITY

-0.06

 McInt

-0.06

 native

-0.06

 rolling

-0.06

 Diego

-0.06

cup

-0.06

 board

-0.06

POSITIVE LOGITS

\R

0.07

dbname

0.06

 raster

0.06

AUT

0.06

。あ

0.06

 Computer

0.06

_build

0.06

mark

0.06

hů

0.06

래

0.06

Activations Density 0.031%

No Known Activations