© 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 · 19-RESID-POST-AA · 72884 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
72884

INDEX

Explanations

population numbers

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

 SUMMARY

-0.08

함

-0.07

bra

-0.07

Lem

-0.07

-0.06

-alone

-0.06

zaz

-0.06

ed

-0.06

 redundant

-0.06

Australia

-0.06

POSITIVE LOGITS

tmpl

0.07

_cert

0.07

subscription

0.06

-chart

0.06

_ENTER

0.06

 فض

0.06

듯

0.06

튜

0.06

 enabling

0.06

_Ass

0.06

Activations Density 0.029%

No Known Activations