INDEX

Explanations

references to academic research and studies across various disciplines

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

oba

-0.18

abcdefghijklmnop

-0.17

UIAlert

-0.14

éĤ¦

-0.13

ABCDEFGHIJKLMNOP

-0.13

abcdefghijkl

-0.13

ddy

-0.13

 Bale

-0.13

Ð½Ð¸ÑĤ

-0.13

 Ð¼Ð°Ð½

-0.13

POSITIVE LOGITS

 topics

0.21

 Thema

0.17

 topic

0.16

 Topics

0.15

 subjects

0.15

 relevant

0.15

 areas

0.15

 Shah

0.15

topic

0.15

 Ã¡rea

0.15

Activations Density 0.154%

references to academic research and studies across various disciplines

No Comments

No Known Activations