INDEX

Explanations

abbreviations and acronyms related to organizations and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

+xml

-0.16

 heavens

-0.15

 breat

-0.14

DataStream

-0.14

ë£Į

-0.14

wner

-0.14

nick

-0.13

achers

-0.13

EndInit

-0.13

xls

-0.13

POSITIVE LOGITS

CC

0.19

AA

0.17

clc

0.15

utherland

0.14

¢

0.14

 {{--<

0.14

cies

0.14

AC

0.14

 Sharma

0.14

cast

0.13

Activations Density 0.373%

abbreviations and acronyms related to organizations and programs

No Comments

No Known Activations