INDEX

Explanations

technical terms and references related to programming and data structures

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

 industri

-0.16

Î¿ÏħÏĥ

-0.15

rase

-0.14

 leverage

-0.14

TCL

-0.14

strand

-0.13

izen

-0.13

fos

-0.13

fi

-0.13

 éģ

-0.13

POSITIVE LOGITS

ihat

0.17

ovit

0.16

$__

0.15

pcodes

0.14

UED

0.14

Ð°ÑģÑĤÐ¸

0.14

ories

0.14

olars

0.14

Ã§ok

0.14

 Stap

0.14

Activations Density 0.005%

technical terms and references related to programming and data structures

No Comments

No Known Activations