INDEX

Explanations

technical terms and concepts related to software and plugins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

arie

-0.15

Ø±ÙĪÛĮ

-0.15

éĹ

-0.14

snd

-0.14

steen

-0.14

Tro

-0.14

 Zaman

-0.14

.scalablytyped

-0.14

 CircularProgress

-0.13

 administration

-0.13

POSITIVE LOGITS

rig

0.30

Rig

0.29

 rigs

0.28

 Maya

0.26

rig

0.26

 rigged

0.25

 motion

0.24

 Motion

0.24

IK

0.23

moc

0.23

Activations Density 0.027%

technical terms and concepts related to software and plugins

No Comments

No Known Activations