INDEX

Explanations

key indicators of a publication or an online platform's features

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

anks

-0.15

.SwingConstants

-0.13

ay

-0.13

znik

-0.13

 historic

-0.13

ijo

-0.13

uj

-0.13

uji

-0.13

amp

-0.13

orr

-0.12

POSITIVE LOGITS

ForResource

0.15

atego

0.14

egie

0.14

ä»¥ä¸Ĭ

0.14

INLINE

0.14

nThe

0.13

 Ú¯ÛĮØ±ÛĮ

0.13

ÑĩÐ¸Ð½

0.13

ï¸

0.13

Č↵

0.12

Activations Density 0.307%

key indicators of a publication or an online platform's features

No Comments

No Known Activations