INDEX

Explanations

mathematical terms related to shapes and sequences in geometry

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

REFERRED

-0.06

 Pistol

-0.06

wick

-0.06

ALLE

-0.06

 ChÃŃ

-0.06

.ns

-0.06

iddet

-0.06

atÃ¼rk

-0.06

ugen

-0.06

assen

-0.06

POSITIVE LOGITS

 Highlands

0.06

Fi

0.06

 pros

0.06

ortex

0.06

Fem

0.06

å°ļ

0.06

Bru

0.06

 ther

0.06

Hal

0.06

Hal

0.05

Activations Density 0.196%

mathematical terms related to shapes and sequences in geometry

No Comments

No Known Activations