© 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 · 112849 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
112849

INDEX

Explanations

ap

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

 bugs

-0.08

 breakfast

-0.07

 ware

-0.07

 bond

-0.07

 brunch

-0.07

 Wouldn

-0.07

لو

-0.07

-0.07

 bolts

-0.06

ari

-0.06

POSITIVE LOGITS

Inverse

0.07

 Держав

0.06

Searching

0.06

 konu

0.06

-ap

0.06

�

0.06

-г

0.06

 negligent

0.06

 ГО

0.06

 Rück

0.06

Activations Density 0.015%

No Known Activations