INDEX

Explanations

code

np_max-act · gemini-2.0-flash

code snippets related to defining classes and methods in programming languages, specifically Java.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lemon

-0.07

ervals

-0.07

Src

-0.06

 damage

-0.06

Book

-0.06

 blob

-0.06

 Mouse

-0.06

loads

-0.06

-len

-0.06

 Professionals

-0.06

POSITIVE LOGITS

 Serge

0.07

nj

0.07

cet

0.07

 Đảng

0.06

เทศ

0.06

企

0.06

鉄道

0.06

卡

0.06

>",

0.06

Activations Density 0.008%

code

code snippets related to defining classes and methods in programming languages, specifically Java.

No Comments

No Known Activations