INDEX

Explanations

technical terms related to software and file management

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bourg

-0.17

otec

-0.16

CardContent

-0.14

opro

-0.14

esub

-0.14

/*č↵

-0.14

usted

-0.14

illy

-0.14

batim

-0.14

çĤ

-0.14

POSITIVE LOGITS

 option

0.18

 options

0.17

 settings

0.16

 selections

0.15

options

0.15

utra

0.15

mirror

0.15

 setting

0.15

 selecting

0.14

-settings

0.14

Activations Density 0.065%

technical terms related to software and file management

No Comments

No Known Activations