© 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 · 7-RESID-POST-AA · 130348 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
130348

INDEX

Explanations

correct

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

.Attributes

-0.07

_fore

-0.06

ूच

-0.06

응

-0.06

 Connecticut

-0.06

 Judith

-0.06

ModelError

-0.06

ět

-0.06

이지

-0.06

 cooperate

-0.06

POSITIVE LOGITS

meniz

0.07

their

0.07

.turn

0.07

єн

0.06

 resmi

0.06

<l

0.06

getSimpleName

0.06

 Shard

0.06

 grands

0.06

nextInt

0.06

Activations Density 0.020%

No Known Activations