INDEX

Explanations

references to specific weeks, seasons, or fiscal years in a document

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

ãĥ¼ãĥ³

-0.14

 fitted

-0.14

-0.13

ari

-0.13

way

-0.13

_LICENSE

-0.13

Kro

-0.13

Way

-0.13

alg

-0.13

POSITIVE LOGITS

oldt

0.15

 pokoj

0.15

ROTO

0.14

 defaultManager

0.14

erer

0.13

mÃ®

0.13

 GANG

0.13

bk

0.13

Ð¾ÑĢÐ¾Ð´

0.13

.handlers

0.13

Activations Density 0.238%

references to specific weeks, seasons, or fiscal years in a document

No Comments

No Known Activations