INDEX

Explanations

actions related to updating, changing, or altering content or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

orris

-0.14

 Ø¥ÙĦ

-0.14

ially

-0.14

getter

-0.14

ãĤ¹ãĤ¯

-0.13

ERRU

-0.13

bearer

-0.13

oÅĻ

-0.13

agnost

-0.13

/people

-0.13

POSITIVE LOGITS

/re

0.37

/ref

0.31

/rec

0.30

/reset

0.30

/update

0.29

old

0.29

/rem

0.28

/up

0.27

/red

0.27

(old

0.26

Activations Density 0.138%

actions related to updating, changing, or altering content or processes

No Comments

No Known Activations