INDEX

Explanations

phrases that indicate methods, approaches, or pathways to achieve certain outcomes

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

ard

-0.08

DataContext

-0.07

orro

-0.07

à¹Ĩ

-0.07

ekler

-0.06

Sto

-0.06

arch

-0.06

 à¹Ĩ

-0.06

allo

-0.06

OUCH

-0.06

POSITIVE LOGITS

ltra

0.07

á»ĭ

0.07

ment

0.06

ãģĳãĤĮãģ©

0.06

à¸£à¸ª

0.06

edio

0.06

prÃ¼

0.06

(strict

0.06

 serialVersionUID

0.06

naire

0.06

Activations Density 0.048%

phrases that indicate methods, approaches, or pathways to achieve certain outcomes

No Comments

No Known Activations