INDEX

Explanations

information related to services, offerings, and usage in various contexts

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

itol

-0.15

 baud

-0.14

 çħ

-0.14

ainment

-0.14

æ¹¾

-0.14

 Ø§ÙĦØªØ³

-0.14

 åĴ

-0.13

ãĥ§

-0.13

ails

-0.13

iol

-0.13

POSITIVE LOGITS

 also

0.24

also

0.21

Also

0.21

ä¹Łä¸į

0.19

 ALSO

0.18

 Also

0.17

ä¹Łæľī

0.17

 occasional

0.17

other

0.16

Non

0.16

Activations Density 0.118%

information related to services, offerings, and usage in various contexts

No Comments

No Known Activations