INDEX

Explanations

references to individuals and their familial or professional identities

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

ount

-0.16

 Singular

-0.15

OUNT

-0.15

 dara

-0.15

 SelectList

-0.14

ietf

-0.14

anzeigen

-0.13

éĴ

-0.13

leton

-0.13

å¶

-0.13

POSITIVE LOGITS

&view

0.15

ILT

0.14

ibri

0.14

#ab

0.14

.(*

0.14

 PrvnÃŃ

0.13

 ÙĪØ±Ø²

0.13

ARGV

0.13

à¸²à¸

0.13

 ((__

0.13

Activations Density 0.049%

references to individuals and their familial or professional identities

No Comments

No Known Activations