INDEX

Explanations

phrases related to mathematical expansion and simplification

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zelf

-0.07

htub

-0.07

ernen

-0.07

ãģ¥

-0.06

AMS

-0.06

statt

-0.06

othy

-0.06

Ú©Ø±ÛĮ

-0.06

aida

-0.06

 Columbia

-0.06

POSITIVE LOGITS

0.07

ilip

0.07

ToFit

0.07

ãĥ¼ãĥĳãĥ¼

0.06

ague

0.06

å±ķ

0.06

-disable

0.06

ÙĦÛĮØ³

0.06

.opensource

0.06

Activations Density 0.067%

phrases related to mathematical expansion and simplification

No Comments

No Known Activations