INDEX

Explanations

instances of confrontation or contention within various contexts

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

bes

-0.17

ons

-0.15

Ã©rc

-0.15

Ø°

-0.14

 Bryan

-0.14

Cot

-0.14

 rough

-0.13

 late

-0.13

ampion

-0.13

POSITIVE LOGITS

uen

0.18

çĮĽ

0.15

vanced

0.14

presso

0.14

Sortable

0.14

iores

0.14

WithEmail

0.14

onomous

0.14

otlin

0.13

-ng

0.13

Activations Density 0.221%

instances of confrontation or contention within various contexts

No Comments

No Known Activations