INDEX

Explanations

technical terms related to databases and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 concrete

-0.17

ãģĭãģĳ

-0.17

Concrete

-0.16

 Concrete

-0.16

à¸¹à¸¡

-0.15

 fore

-0.14

riday

-0.14

usting

-0.14

InnerText

-0.14

ohn

-0.13

POSITIVE LOGITS

SAS

0.22

APE

0.17

Sas

0.16

 âĹĦ

0.16

WebpackPlugin

0.15

andid

0.14

 Statistics

0.14

uta

0.14

 kraj

0.14

 Bones

0.14

Activations Density 0.012%

technical terms related to databases and programming

No Comments

No Known Activations