INDEX

Explanations

phrases indicating causation or conditions

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

NotSupportedException

-0.14

ildo

-0.14

eca

-0.14

ohana

-0.13

ount

-0.13

áº¿t

-0.13

iro

-0.13

Ð»ÑĮ

-0.13

ariat

-0.13

ãĥŃãĥ¼

-0.12

POSITIVE LOGITS

ides

0.15

akes

0.14

aney

0.14

cctor

0.13

att

0.13

ÐµÐ´ÑĮ

0.13

adora

0.13

 Hole

0.13

Naz

0.13

Activations Density 0.120%

phrases indicating causation or conditions

No Comments

No Known Activations