INDEX

Explanations

expressions that highlight uniqueness or exclusivity

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

ISTA

-0.15

echa

-0.14

atz

-0.13

ixel

-0.13

å°ĳå¥³

-0.13

avit

-0.13

antine

-0.13

 Gulf

-0.13

utral

-0.13

POSITIVE LOGITS

nor

0.28

 anymore

0.22

nor

0.19

Nor

0.18

 Ø¨ÙĦÚ©Ùĩ

0.17

Nor

0.16

eward

0.15

(CharSequence

0.15

 Hamp

0.14

-exclusive

0.14

Activations Density 0.029%

expressions that highlight uniqueness or exclusivity

No Comments

No Known Activations