INDEX

Explanations

references to email communications and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Telegram

-0.16

unc

-0.15

 tweets

-0.14

bÃŃ

-0.14

tweets

-0.14

steen

-0.13

·

-0.13

cripts

-0.13

Backing

-0.13

aber

-0.13

POSITIVE LOGITS

 subject

0.30

 attachments

0.29

 Subject

0.29

subject

0.28

Subject

0.28

 SUBJECT

0.26

 attachment

0.26

 SMTP

0.26

 receivers

0.25

 Attach

0.25

Activations Density 0.037%

references to email communications and related activities

No Comments

No Known Activations