INDEX

Explanations

mathematical terms and references related to calculations, coordinates, and formulas

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

 zwar

-0.07

oÅ¾

-0.07

Ä©

-0.07

çĽĳåĲ¬é¡µéĿ¢

-0.07

lah

-0.07

ickerView

-0.06

.userInteractionEnabled

-0.06

atatype

-0.06

ednou

-0.06

XA

-0.06

POSITIVE LOGITS

ä»»ä½ķ

0.08

↵

0.08

any

0.07

nor

0.07

 anymore

0.07

 anyone

0.07

yet

0.07

 anything

0.07

 slightest

0.06

Activations Density 0.111%

mathematical terms and references related to calculations, coordinates, and formulas

No Comments

No Known Activations