© 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 · 35976 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
35976

INDEX

Explanations

setUp

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

/node

-0.07

ग

-0.06

ерше

-0.06

perc

-0.06

conj

-0.06

/**/*.

-0.06

ici

-0.06

활동

-0.06

chsel

-0.06

_that

-0.06

POSITIVE LOGITS

 setUp

0.12

 tearDown

0.10

.setUp

0.08

ぬ

0.06

(td

0.06

 Resolution

0.06

(ErrorMessage

0.06

 Huff

0.06

 Symbol

0.06

tearDown

0.06

Activations Density 0.000%

No Known Activations