INDEX

Explanations

chemical descriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 probation

-0.07

드로

-0.07

 wizards

-0.07

 cruc

-0.07

 Estr

-0.06

こんに

-0.06

数

-0.06

saida

-0.06

suffix

-0.06

POSITIVE LOGITS

_native

0.06

#[

0.06

Osc

0.06

 Regex

0.06

LayoutManager

0.06

Zen

0.06

Indicator

0.06

 interpreting

0.06

ève

0.06

ナ

0.06

Activations Density 0.052%

chemical descriptions

No Comments

No Known Activations

chemical descriptions

No Comments

No Known Activations