INDEX

Explanations

instances of the article "a" related to various types of informational content, such as definitions, descriptions, and notices

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

à¸²à¸¨

-0.16

eba

-0.16

,ep

-0.15

itat

-0.14

ãĥ¼ãĥ©

-0.14

 æĻ

-0.14

 kabil

-0.14

adero

-0.14

irie

-0.13

POSITIVE LOGITS

 list

0.19

 guest

0.19

 follow

0.19

 placeholder

0.19

 Sponsored

0.18

 repost

0.17

 sponsored

0.17

 companion

0.17

 tale

0.17

 Guest

0.16

Activations Density 0.047%

instances of the article "a" related to various types of informational content, such as definitions, descriptions, and notices

No Comments

No Known Activations