INDEX

Explanations

technical terms and references, particularly in programming and data structures

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/embed

-0.16

ersistence

-0.16

eri

-0.14

åĽ½äº§

-0.13

 ÏĥÎ¿Ïħ

-0.13

WEBPACK

-0.13

olls

-0.13

ä¼łå¥ĩ

-0.13

 ÑĢÐ°Ð·

-0.12

ovic

-0.12

POSITIVE LOGITS

oyer

0.15

oom

0.15

å´İ

0.14

-------------</

0.14

yre

0.14

ardy

0.14

izedName

0.13

ifle

0.13

aily

0.12

Activations Density 0.167%

technical terms and references, particularly in programming and data structures

No Comments

No Known Activations