INDEX

Explanations

mathematical expressions and relationships involving geometric figures

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

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

-0.07

edy

-0.07

-lnd

-0.06

ĵn

-0.06

iddi

-0.06

erala

-0.06

ained

-0.06

uers

-0.06

iswa

-0.06

ediator

-0.06

POSITIVE LOGITS

ugin

0.07

æģ©

0.07

LOAT

0.07

Ø§Ø±Ùģ

0.06

Ã²ng

0.06

onso

0.06

yc

0.06

à¸²à¸¨

0.06

Ļ¨

0.06

EndPoint

0.06

Activations Density 0.244%

mathematical expressions and relationships involving geometric figures

No Comments

No Known Activations