INDEX

Explanations

nouns related to various products and their characteristics

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

assin

-0.15

 hell

-0.15

eness

-0.15

 Virt

-0.14

ensively

-0.13

emark

-0.13

 Foley

-0.13

comm

-0.13

unp

-0.12

POSITIVE LOGITS

 DÃ¼n

0.14

WithMany

0.14

USA

0.13

OwnProperty

0.13

ymous

0.13

ackers

0.13

Ð¸ÑĨÐ¸Ð½

0.13

.onerror

0.13

à¥įà¤°à¤¸

0.12

avid

0.12

Activations Density 0.163%

nouns related to various products and their characteristics

No Comments

No Known Activations