INDEX

Explanations

references to available resources or services in a technical context

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

nten

-0.13

iku

-0.13

 also

-0.13

yas

-0.13

 info

-0.12

tres

-0.12

Ã²n

-0.12

Ìģ

-0.12

 ayrÄ±ca

-0.12

POSITIVE LOGITS

.scalablytyped

0.19

StateToProps

0.14

ommen

0.14

iddy

0.14

 DependencyProperty

0.13

ìŀĸ

0.13

TestFixture

0.13

Ä±zÄ±

0.13

Ð³ÑĢÐ°Ð´

0.12

.ToShort

0.12

Activations Density 0.004%

references to available resources or services in a technical context

No Comments

No Known Activations