INDEX

Explanations

phrases related to customization and personalization options

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

cott

-0.19

tÃ©

-0.16

iaux

-0.16

tah

-0.15

ugu

-0.15

.fold

-0.14

 PROGMEM

-0.14

PLIED

-0.14

eks

-0.14

ahi

-0.14

POSITIVE LOGITS

 suits

0.29

 best

0.26

 fits

0.22

 suited

0.22

fit

0.22

best

0.22

fits

0.21

 phÃ¹

0.20

 suit

0.19

-su

0.19

Activations Density 0.123%

phrases related to customization and personalization options

No Comments

No Known Activations