INDEX

Explanations

phrases and words associated with inquiries or requests for information

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

 calls

-0.20

 contacting

-0.20

 Contacts

-0.19

 Contact

-0.19

Contact

-0.19

 call

-0.19

 Calls

-0.18

 CONTACT

-0.18

call

-0.18

 contact

-0.18

POSITIVE LOGITS

 schedule

0.32

 scheduling

0.29

schedule

0.28

 arrange

0.28

 schedules

0.27

 discuss

0.26

 Schedule

0.26

 arrangements

0.25

 arrangement

0.24

 arranging

0.23

Activations Density 0.066%

phrases and words associated with inquiries or requests for information

No Comments

No Known Activations