INDEX

Explanations

observed

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_heat

-0.07

 dinheiro

-0.07

 little

-0.07

_INIT

-0.07

via

-0.07

 ring

-0.06

DIN

-0.06

_join

-0.06

 bigger

-0.06

POSITIVE LOGITS

 observed

0.10

 observable

0.09

 observation

0.09

 observe

0.09

 observing

0.09

 observations

0.08

observ

0.08

 observ

0.08

 Observatory

0.08

 Observer

0.08

Activations Density 0.025%

observed

No Comments

No Known Activations

observed

No Comments

No Known Activations