© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 55932 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
55932

INDEX

Explanations

sports team win

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

操作

-0.07

길

-0.07

 simulations

-0.07

condition

-0.07

길

-0.06

bots

-0.06

馬

-0.06

โด

-0.06

 bots

-0.06

 код

-0.06

POSITIVE LOGITS

 UserId

0.07

 paramMap

0.07

 saja

0.06

uably

0.06

jí

0.06

 unut

0.06

issing

0.06

 fikir

0.06

ổng

0.06

 quaint

0.06

Activations Density 0.020%

No Known Activations