INDEX

Explanations

references to daily routines and transitions from day to night

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 breakfast

-0.37

 Breakfast

-0.36

 Morning

-0.29

 mornings

-0.28

 brunch

-0.28

 dawn

-0.28

 sunrise

-0.27

 morning

-0.27

Morning

-0.26

 Sunrise

-0.20

POSITIVE LOGITS

 evening

0.40

æĻļ

0.39

 tonight

0.35

 Ð²ÐµÑĩ

0.35

 evenings

0.35

 Tonight

0.34

Tonight

0.32

 nightly

0.30

 Evening

0.30

 veÄįer

0.27

Activations Density 0.221%

references to daily routines and transitions from day to night

No Comments

No Known Activations