INDEX

Explanations

references to programming classes and methods, particularly those related to Java libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

urge

-0.17

ovol

-0.16

itel

-0.16

uchen

-0.15

Å¡ov

-0.14

ÙİØŃ

-0.14

rze

-0.14

ocache

-0.13

 emanc

-0.13

POSITIVE LOGITS

.io

0.17

ICY

0.14

StringEncoding

0.14

-lite

0.14

.utils

0.14

ay

0.14

Nar

0.14

ignum

0.13

/ion

0.13

ced

0.13

Activations Density 0.045%

references to programming classes and methods, particularly those related to Java libraries

No Comments

No Known Activations