INDEX

Explanations

function calls related to removing or unregistering items in a database or system

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

idor

-0.15

leta

-0.15

 Ð¿Ð¾Ð±

-0.14

/cal

-0.14

_UNDEFINED

-0.14

 ÑĢÐ°ÑģÐº

-0.13

ŀæĢ§

-0.13

owie

-0.13

æģ

-0.13

orting

-0.13

POSITIVE LOGITS

usk

0.16

æİī

0.16

 khá»ıi

0.16

 flush

0.15

gence

0.14

 removes

0.14

èģĺ

0.14

 remove

0.13

IfExists

0.13

erp

0.13

Activations Density 0.054%

function calls related to removing or unregistering items in a database or system

No Comments

No Known Activations