INDEX

Explanations

structured numerical data and lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Pill

-0.16

 Platinum

-0.15

 Pearce

-0.15

ekim

-0.15

 Pierce

-0.15

 Pruitt

-0.15

Khu

-0.15

æŀ

-0.14

ĥ½

-0.14

 Pleasant

-0.14

POSITIVE LOGITS

 page

0.65

page

0.56

 pages

0.55

-page

0.53

 Page

0.52

Page

0.51

_page

0.50

.page

0.47

	page

0.45

 pagina

0.44

Activations Density 0.190%

structured numerical data and lists

No Comments

No Known Activations