INDEX

Explanations

actions and phrases related to assistance and making requests for help

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

 láº«n

-0.16

inq

-0.14

ÏģÎ¿Ïį

-0.13

 interpret

-0.13

 testament

-0.13

 mere

-0.13

ÐµÐ½Ñı

-0.13

Vor

-0.13

oru

-0.13

collapsed

-0.13

POSITIVE LOGITS

 manually

0.15

 alternatives

0.14

 manual

0.14

)|(

0.14

posables

0.14

 elsewhere

0.14

ÏĥÏĦÎµ

0.14

emoc

0.13

æĵ

0.13

å¼¥

0.13

Activations Density 0.196%

actions and phrases related to assistance and making requests for help

No Comments

No Known Activations