INDEX

Explanations

instances of prominent phrases or objects that signify cultural or religious symbols

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

uur

-0.14

ohan

-0.13

vier

-0.13

gesi

-0.13

ecs

-0.13

 kolo

-0.13

 vÃ²ng

-0.13

Ø®Ø§ÙĨÙĩ

-0.13

kaÃ§

-0.13

oret

-0.13

POSITIVE LOGITS

 world

0.16

agal

0.15

ndern

0.15

Æ°a

0.14

uben

0.13

 leading

0.13

ãĥĥãĥĦ

0.13

venes

0.13

izz

0.13

 nations

0.13

Activations Density 0.126%

instances of prominent phrases or objects that signify cultural or religious symbols

No Comments

No Known Activations