INDEX

Explanations

orse

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 screening

-0.07

.AlertDialog

-0.07

 finder

-0.07

 Bayer

-0.07

 Reuters

-0.06

 weaker

-0.06

CCR

-0.06

_parameter

-0.06

experimental

-0.06

POSITIVE LOGITS

 horse

0.11

 Horse

0.09

 horses

0.09

orse

0.07

horse

0.07

 hafif

0.07

Ens

0.07

mot

0.07

 horsepower

0.06

orses

0.06

Activations Density 0.009%

orse

No Comments

No Known Activations