INDEX

Explanations

phrases that indicate the extent or range of something

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

awei

-0.20

inger

-0.16

linger

-0.15

aida

-0.15

isia

-0.15

 yaÅŁÄ±nda

-0.15

emain

-0.14

aign

-0.14

ISE

-0.14

INGER

-0.14

POSITIVE LOGITS

 scope

0.24

 scopes

0.21

 Scope

0.20

Scope

0.18

scopes

0.17

(scope

0.17

extent

0.17

scope

0.16

 extent

0.16

èĮĥåĽ´

0.16

Activations Density 0.079%

phrases that indicate the extent or range of something

No Comments

No Known Activations