INDEX

Explanations

technical terms and operations related to software and files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

een

-0.16

bih

-0.15

to

-0.15

 sight

-0.14

StateChanged

-0.14

á»Ŀ

-0.14

aeper

-0.14

dge

-0.14

ror

-0.14

zc

-0.14

POSITIVE LOGITS

ces

0.18

icode

0.17

.si

0.16

 FROM

0.15

 from

0.15

icits

0.14

 Pant

0.14

usic

0.14

endants

0.14

 Planner

0.14

Activations Density 0.196%

technical terms and operations related to software and files

No Comments

No Known Activations