© 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 · 53719 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
53719

INDEX

Explanations

movie

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

TT

-0.08

ethoven

-0.07

ves

-0.06

 آزمون

-0.06

 Cleaning

-0.06

峰

-0.06

lescope

-0.06

TEN

-0.06

xz

-0.06

.widgets

-0.06

POSITIVE LOGITS

0.06

&);↵↵

0.06

because

0.06

 forfe

0.06

 '');

0.06

])↵↵↵

0.06

<Animator

0.06

_Filter

0.06

(next

0.06

ожет

0.06

Activations Density 0.027%

No Known Activations