INDEX

Explanations

mathematical expressions and equations

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

enh

-0.07

sl

-0.06

Ps

-0.06

 responsible

-0.06

WWW

-0.06

LS

-0.06

 shell

-0.06

inks

-0.06

POSITIVE LOGITS

GINE

0.07

csi

0.07

 GOODMAN

0.07

ÙĨØ´

0.07

SetBranch

0.07

UCH

0.06

areth

0.06

STALL

0.06

erce

0.06

rica

0.06

Activations Density 0.184%

mathematical expressions and equations

No Comments

No Known Activations