INDEX

Explanations

phrases that discuss mathematical problems and their complexities

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

/REC

-0.07

ÑģÐ¾ÑĤ

-0.07

Ð¾ÑģÑĥÐ´

-0.06

ansi

-0.06

ÑħÐ¾

-0.06

 podrob

-0.06

iw

-0.06

ãĤ¡

-0.06

ãģıãģł

-0.06

ãĥ¼ãĥĭ

-0.06

POSITIVE LOGITS

èĬ³

0.07

eled

0.07

sop

0.07

ipes

0.06

EP

0.06

Nap

0.06

 Bron

0.06

fl

0.06

DP

0.06

Activations Density 0.073%

phrases that discuss mathematical problems and their complexities

No Comments

No Known Activations