© 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 · 7-RESID-POST-AA · 27007 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
27007

INDEX

Explanations

punctuation

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

میل

-0.06

ÓN

-0.06

_learn

-0.06

۷

-0.06

-automatic

-0.06

_sg

-0.06

 planetary

-0.06

NORMAL

-0.06

idi

-0.06

君

-0.06

POSITIVE LOGITS

 ""))↵

0.07

renders

0.06

tent

0.06

，不

0.06

 consumers

0.06

AA

0.06

CGFloat

0.06

duct

0.06

tel

0.06

 pledged

0.06

Activations Density 0.002%

No Known Activations