INDEX

Explanations

introductory phrases often used in mathematical explanations

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¹¾

-0.07

asename

-0.06

à¤¹à¤°

-0.06

 Strom

-0.06

á»Ľm

-0.06

	Copyright

-0.06

alle

-0.06

 Dimit

-0.06

iod

-0.06

ille

-0.06

POSITIVE LOGITS

ëł¨

0.07

rides

0.07

 ÙħÙĤØ¯Ùħ

0.06

cta

0.06

noinspection

0.06

Ð¾Ð½Ð¸

0.06

å¥ı

0.06

ãĤīãģĦ

0.06

IRC

0.06

Activations Density 0.105%

introductory phrases often used in mathematical explanations

No Comments

No Known Activations