INDEX

Explanations

phrases related to verification and checking calculations

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

azen

-0.07

.Compute

-0.06

 among

-0.06

 NotFoundException

-0.06

ature

-0.06

 McKin

-0.06

AdapterFactory

-0.06

par

-0.05

ATURE

-0.05

 schÃ¶n

-0.05

POSITIVE LOGITS

ime

0.07

0.06

ijkstra

0.06

yntax

0.06

ascript

0.06

 nonatomic

0.06

IME

0.06

-double

0.06

Activations Density 0.054%

phrases related to verification and checking calculations

No Comments

No Known Activations