© 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 · 53713 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
53713

INDEX

Explanations

connector

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

 defaultdict

-0.07

ot

-0.07

_DO

-0.07

.plot

-0.06

 cheered

-0.06

ět

-0.06

徒

-0.06

-elect

-0.06

 yetiştir

-0.06

 Germans

-0.06

POSITIVE LOGITS

Around

0.06

QueryParam

0.06

ungeons

0.06

:[[

0.06

znam

0.05

","",

0.05

0.05

 Estados

0.05

igail

0.05

ToRemove

0.05

Activations Density 0.013%

No Known Activations