INDEX

Explanations

phrases indicating the parts of a proof.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L11R

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.11.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

illis

-0.07

ÑĨÐµÐ·

-0.07

orph

-0.06

uta

-0.06

DDD

-0.06

uellement

-0.06

Į¨

-0.06

.cod

-0.06

iev

-0.06

enge

-0.06

POSITIVE LOGITS

Ð°Ð½Ð¸ÑĨ

0.07

 disap

0.06

orex

0.06

ãĥ³ãĥĩ

0.06

atore

0.06

ĥn

0.06

 Ð¼ÑĸÑģÑı

0.06

yled

0.06

 Derrick

0.06

Î·Î³

0.06

Activations Density 0.244%

phrases indicating the parts of a proof.

No Comments

No Known Activations