INDEX

Explanations

technical terms and phrases related to scientific instruments and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Obr

-0.15

 recursively

-0.14

 ping

-0.14

forge

-0.14

 epis

-0.13

 Strauss

-0.13

 recurrent

-0.13

fiz

-0.13

/render

-0.13

 Casual

-0.13

POSITIVE LOGITS

 column

0.27

el

0.27

 Column

0.26

-column

0.25

Columns

0.25

 mobile

0.25

Column

0.25

 columns

0.25

 Columns

0.24

.column

0.23

Activations Density 0.023%

technical terms and phrases related to scientific instruments and data analysis

No Comments

No Known Activations