© 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 · 47201 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
47201

INDEX

Explanations

delhi

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

 rounded

-0.07

 Quran

-0.07

oy

-0.06

ason

-0.06

_cmp

-0.06

งของ

-0.06

(am

-0.06

œ

-0.06

payment

-0.06

런

-0.06

POSITIVE LOGITS

 Delhi

0.16

WithEmail

0.07

 Capitol

0.07

 dál

0.06

 plague

0.06

 cùng

0.06

Too

0.06

าษฎ

0.06

 murky

0.06

DAL

0.06

Activations Density 0.001%

No Known Activations