INDEX

Explanations

references to popular culture and collective memory

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

.SingleOrDefault

-0.15

oundary

-0.15

ynes

-0.14

æ¼Ĥ

-0.14

 Scenario

-0.14

loquent

-0.13

 scenarios

-0.13

 Friedman

-0.13

yne

-0.13

#__

-0.13

POSITIVE LOGITS

azzi

0.15

zew

0.14

ascal

0.14

orte

0.14

oldem

0.13

vor

0.13

athi

0.13

ducted

0.13

explode

0.13

TOTYPE

0.13

Activations Density 0.257%

references to popular culture and collective memory

No Comments

No Known Activations