© 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 · 30759 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
30759

INDEX

Explanations

Air

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

posite

-0.07

 Його

-0.07

.redis

-0.06

.tile

-0.06

 hacked

-0.06

odo

-0.06

Ids

-0.06

 sayı

-0.06

Equality

-0.06

 biomass

-0.06

POSITIVE LOGITS

募

0.07

进

0.07

กำล

0.07

_DBG

0.06

DRAM

0.06

 quar

0.06

ketøy

0.06

 phoenix

0.06

�

0.06

 ADDR

0.06

Activations Density 0.006%

No Known Activations