© 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 · 33193 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
33193

INDEX

Explanations

incubator

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

.ORDER

-0.07

 आत

-0.07

.wikipedia

-0.07

 Solve

-0.06

●●●●

-0.06

 спос

-0.06

 climax

-0.06

-0.06

 undergoing

-0.06

 παι

-0.06

POSITIVE LOGITS

 incub

0.10

ůr

0.07

 Sebast

0.07

bit

0.06

 Herbert

0.06

long

0.06

ator

0.06

 Lucy

0.06

िक

0.06

 indicator

0.06

Activations Density 0.001%

No Known Activations