INDEX

Explanations

technical terms related to software features and functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

lej

-0.15

ASP

-0.14

PostBack

-0.14

ãĤ«ãĥ¼

-0.14

ASIC

-0.14

 Jennings

-0.14

HeaderCode

-0.14

PHPExcel

-0.14

orelease

-0.13

.asp

-0.13

POSITIVE LOGITS

 gnome

0.35

 GNOME

0.34

gtk

0.28

GTK

0.28

.desktop

0.27

 Plasma

0.27

 plasma

0.27

KDE

0.26

GN

0.25

 Unity

0.25

Activations Density 0.077%

technical terms related to software features and functionalities

No Comments

No Known Activations