INDEX

Explanations

phrases indicating an action or goal

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UIScreen

-0.07

 !***

-0.07

à¹Ģà¸¥à¸¢

-0.06

/Internal

-0.06

 ragaz

-0.06

?>/

-0.06

ionario

-0.06

Ð²Ñĭ

-0.06

akers

-0.06

 Vital

-0.06

POSITIVE LOGITS

inel

0.07

Ã¹a

0.06

omore

0.06

ernote

0.06

kin

0.06

çīĩ

0.06

ives

0.06

erre

0.06

IGH

0.06

asion

0.06

Activations Density 0.059%

phrases indicating an action or goal

No Comments

No Known Activations