INDEX

Explanations

mathematical symbols and notations related to dimensional analysis

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LES

-0.18

ÅĤÄħ

-0.15

Ø§Ø¶

-0.14

cul

-0.14

annies

-0.14

lamaz

-0.13

èĹı

-0.13

cul

-0.13

lsen

-0.13

ving

-0.13

POSITIVE LOGITS

udit

0.17

zl

0.16

fold

0.16

arda

0.15

 addCriterion

0.14

ActionCreators

0.14

chluss

0.14

 voks

0.14

 Placement

0.13

ites

0.13

Activations Density 0.299%

mathematical symbols and notations related to dimensional analysis

No Comments

No Known Activations