INDEX

Explanations

references to PDF documents and related functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

datable

-0.18

ustr

-0.17

kers

-0.15

@nate

-0.14

ÄĽk

-0.14

Ø¹Ú©Ø³

-0.14

ful

-0.14

kan

-0.13

OURS

-0.13

few

-0.13

POSITIVE LOGITS

0.30

0.24

sand

0.21

sam

0.18

-format

0.18

íĮĮìĿ¼

0.18

 files

0.17

sak

0.17

 format

0.17

 file

0.17

Activations Density 0.020%

references to PDF documents and related functionalities

No Comments

No Known Activations