INDEX

Explanations

technical terminology related to graph theory and its implications in a discussion

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and 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

oleÄį

-0.07

rama

-0.07

 leading

-0.07

les

-0.06

encode

-0.06

abus

-0.06

et

-0.06

wich

-0.06

Ap

-0.06

wh

-0.06

POSITIVE LOGITS

 merely

0.07

ÑħÑĢÐ°Ð½

0.07

oy

0.07

 harmless

0.07

 simplement

0.06

æİ¢

0.06

Bad

0.06

 Shea

0.06

 rede

0.06

kea

0.06

Activations Density 0.028%

technical terminology related to graph theory and its implications in a discussion

No Comments

No Known Activations