© 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 · 86406 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
86406

INDEX

Explanations

we

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

 miscellaneous

-0.07

quisar

-0.07

@JsonProperty

-0.07

foundation

-0.06

두

-0.06

(robot

-0.06

")]

-0.06

AKER

-0.06

emsp

-0.06

ToRemove

-0.06

POSITIVE LOGITS

 '\\'

0.07

 Strict

0.06

_ck

0.06

ISA

0.06

 riff

0.06

 brid

0.06

(reader

0.06

')));↵↵

0.06

Jul

0.06

Caps

0.06

Activations Density 0.092%

No Known Activations