© 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 · 7-RESID-POST-AA · 70377 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
70377

INDEX

Explanations

to

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

 skoro

-0.07

mens

-0.06

γκό

-0.06

мир

-0.06

.tel

-0.06

:'

-0.06

rio

-0.06

 want

-0.06

 able

-0.06

-rounded

-0.06

POSITIVE LOGITS

 огра

0.06

цять

0.06

 PREF

0.06

such

0.06

 الوطني

0.06

{*

0.06

 بازار

0.06

요

0.06

※

0.06

 دارد

0.06

Activations Density 0.024%

No Known Activations