© 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 · 28010 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
28010

INDEX

Explanations

jobs and services

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

位於

-0.06

 الداخ

-0.06

<tr

-0.06

强

-0.06

Sep

-0.06

Lin

-0.06

 promised

-0.06

保证

-0.06

 rowNum

-0.06

-method

-0.06

POSITIVE LOGITS

Haz

0.06

 Českosloven

0.06

_DELETE

0.06

زد

0.06

UnityEngine

0.06

 HOLDERS

0.06

 Analog

0.06

ultimate

0.06

_FEED

0.06

 kinase

0.06

Activations Density 0.123%

No Known Activations