© 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 · 15-RESID-POST-AA · 23650 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
23650

INDEX

Explanations

product descriptions

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

Fair

-0.07

Bru

-0.07

 relevance

-0.07

ürnberg

-0.06

 richness

-0.06

 Stats

-0.06

 Bags

-0.06

 alguns

-0.06

 Nice

-0.06

 yapılan

-0.06

POSITIVE LOGITS

anv

0.07

 dryer

0.06

aN

0.06

_elim

0.06

rist

0.06

 remar

0.06

ايد

0.06

 chtě

0.06

 Romania

0.06

ту

0.06

Activations Density 0.064%

No Known Activations