INDEX

Explanations

functions and methods related to data type conversion and mathematical operations

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

elif

-0.15

 Seymour

-0.15

æ

-0.15

ninger

-0.15

tridge

-0.14

Ã¼z

-0.14

ØºØ§ÙĦ

-0.14

iche

-0.14

ÏĢÎµ

-0.14

icos

-0.14

POSITIVE LOGITS

 Levine

0.18

efon

0.15

 Henderson

0.15

zcze

0.14

ÑģÑĥ

0.14

oric

0.14

loquent

0.13

Â´

0.13

outer

0.13

Activations Density 0.042%

functions and methods related to data type conversion and mathematical operations

No Comments

No Known Activations