© 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 · 21597 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
21597

INDEX

Explanations

However

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

 Jamie

-0.07

итися

-0.07

lista

-0.06

 giai

-0.06

_LD

-0.06

 Powell

-0.06

_contact

-0.06

Equality

-0.06

caf

-0.06

OG

-0.05

POSITIVE LOGITS

Strike

0.07

 shorts

0.06

 However

0.06

XObject

0.06

(distance

0.06

 didn

0.06

 трех

0.06

 cookie

0.06

ml

0.06

can

0.06

Activations Density 0.033%

No Known Activations