INDEX

Explanations

code and math

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

 دختر

-0.06

 Anything

-0.06

 andere

-0.06

 мус

-0.06

Long

-0.06

 doktor

-0.06

т

-0.06

 minimizing

-0.06

_kelas

-0.06

 paralysis

-0.06

POSITIVE LOGITS

 Cement

0.06

 Yankees

0.06

 Scala

0.06

.Wrap

0.06

 aggregates

0.06

_WARNINGS

0.06

ploy

0.06

.ServiceModel

0.06

POSE

0.06

viso

0.06

Activations Density 0.214%

code and math

No Comments

No Known Activations