INDEX

Explanations

discussions about demographics and skill development related to education and employment opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Were

-0.17

Were

-0.16

ilon

-0.15

’ÑıÐ·

-0.14

EqualTo

-0.14

à¸µà¸¢à¸Ķ

-0.13

 Ð½Ð°ÑħÐ¾Ð´

-0.13

Did

-0.13

 correspond

-0.12

 implements

-0.12

POSITIVE LOGITS

is

0.48

 will

0.40

may

0.40

has

0.39

 cannot

0.38

can

0.38

 might

0.36

isn

0.36

 could

0.35

 seems

0.35

Activations Density 3.583%

discussions about demographics and skill development related to education and employment opportunities

No Comments

No Known Activations