© 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 · 22159 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
22159

INDEX

Explanations

itself

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

PHONE

-0.07

bonus

-0.06

NASDAQ

-0.06

(play

-0.06

 exercise

-0.06

طاق

-0.06

你们

-0.06

-digit

-0.06

=open

-0.06

 cycling

-0.06

POSITIVE LOGITS

 itself

0.10

 Headquarters

0.07

 MessageBoxIcon

0.07

 сама

0.07

 těl

0.06

(coeffs

0.06

เอง

0.06

.GUI

0.06

ijkl

0.06

іп

0.06

Activations Density 0.009%

No Known Activations