INDEX

Explanations

scientific terms and phrases related to biomedical research

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

nock

-0.15

hoy

-0.14

ired

-0.14

ilder

-0.14

orts

-0.14

Î³Î¿Ïħ

-0.14

ä»ĭ

-0.13

agens

-0.13

iffin

-0.13

urger

-0.13

POSITIVE LOGITS

={({

0.17

ystack

0.17

hoff

0.15

Ìĥ

0.14

XCT

0.14

kas

0.14

 didFinish

0.13

?family

0.13

ØªØ§Ø¨

0.13

æ²¢

0.13

Activations Density 0.188%

scientific terms and phrases related to biomedical research

No Comments

No Known Activations