INDEX

Explanations

references to manufacturing processes and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

opers

-0.15

insky

-0.15

 volunt

-0.15

æ¯

-0.14

xing

-0.14

 setup

-0.14

ÑĢÐµÑĤÑĮ

-0.14

toc

-0.14

 táº¡p

-0.13

OPER

-0.13

POSITIVE LOGITS

 components

0.25

-components

0.23

components

0.23

 motion

0.22

 Components

0.22

-component

0.21

 Motion

0.21

 component

0.21

_components

0.20

 Controls

0.20

Activations Density 0.205%

references to manufacturing processes and systems

No Comments

No Known Activations