INDEX

Explanations

time-related expressions and mentions of comments or posts

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

Cat

-0.16

cat

-0.15

ÑıÐ²

-0.15

izar

-0.14

ne

-0.13

al

-0.13

ŀĭ

-0.13

uegos

-0.13

Cat

-0.13

sw

-0.13

POSITIVE LOGITS

agra

0.15

ecut

0.15

bases

0.15

ÑĤÑİ

0.14

ä½

0.14

uale

0.14

Ð»ÐµÐ¹

0.14

æĬķæ³¨

0.13

 Clement

0.13

tog

0.13

Activations Density 0.147%

time-related expressions and mentions of comments or posts

No Comments

No Known Activations