INDEX

Explanations

specific dimensions and measurements related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

umin

-0.17

ppard

-0.15

nap

-0.15

omit

-0.14

htub

-0.14

uir

-0.14

ium

-0.14

ÑĢÐµÑģÑĤ

-0.14

Ø¬ÙĦ

-0.14

vÃ©

-0.14

POSITIVE LOGITS

 inches

0.40

 inch

0.38

-inch

0.34

 Inches

0.32

 Inch

0.32

inch

0.31

å¯¸

0.23

_inches

0.21

 Ø§ÛĮÙĨÚĨ

0.20

å°º

0.20

Activations Density 0.091%

specific dimensions and measurements related to products

No Comments

No Known Activations