INDEX

Explanations

mathematical reasoning using coprimes to make inferences

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cak

-0.07

rello

-0.06

entai

-0.06

 Correspond

-0.06

vertise

-0.06

adata

-0.06

èĬ±

-0.06

Sew

-0.06

miner

-0.06

arging

-0.06

POSITIVE LOGITS

áº«n

0.07

 denominator

0.06

egan

0.06

/respond

0.06

iol

0.05

prime

0.05

anan

0.05

lcm

0.05

á»ĭp

0.05

Activations Density 0.158%

mathematical reasoning using coprimes to make inferences

No Comments

No Known Activations