INDEX

Explanations

instances of significant decision points or confirmations within a logical or mathematical reasoning context

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

Negative Logits

NotSupportedException

-0.08

entiful

-0.07

ecute

-0.07

Detail

-0.06

ksam

-0.06

undry

-0.06

à¥įà¤¬

-0.06

:`~

-0.06

esity

-0.06

ÏĦÎ¹ÎºÎ±

-0.06

POSITIVE LOGITS

 Starr

0.06

 screw

0.06

Łèĥ½

0.06

 tÃ©

0.06

Ð½ÐµÑĢ

0.06

avir

0.06

ZW

0.06

.features

0.06

berger

0.05

 Westbrook

0.05

Activations Density 0.001%

instances of significant decision points or confirmations within a logical or mathematical reasoning context

No Known Activations