INDEX

Explanations

references to time-related conditions and operational hours

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Weeks

-0.18

 Dates

-0.17

onth

-0.17

 weeks

-0.16

 fortn

-0.16

 dates

-0.15

dates

-0.15

 Monthly

-0.15

oose

-0.15

-month

-0.15

POSITIVE LOGITS

 morning

0.33

 nighttime

0.32

 evening

0.32

 night

0.32

 noct

0.31

 daytime

0.31

 late

0.30

å¤ľ

0.29

 hours

0.29

 afternoon

0.27

Activations Density 0.364%

references to time-related conditions and operational hours

No Comments

No Known Activations