INDEX

Explanations

numerical data related to performance metrics

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

ard

-0.14

stoff

-0.14

fam

-0.13

ÙĪÛĮÙĩ

-0.12

 list

-0.12

ãģĭãģĳ

-0.12

URLConnection

-0.12

ink

-0.12

 Norris

-0.12

 Boundary

-0.12

POSITIVE LOGITS

 overall

0.18

 Overall

0.17

 trends

0.16

overall

0.16

 trending

0.15

akra

0.15

icolon

0.15

Overall

0.14

ereco

0.14

dle

0.14

Activations Density 0.163%

numerical data related to performance metrics

No Comments

No Known Activations