INDEX

Explanations

references to "night," particularly in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 mornings

-0.27

 Morning

-0.26

 morning

-0.24

 daytime

-0.24

 noon

-0.23

Morning

-0.23

 Noon

-0.21

 Lunch

-0.21

 lunch

-0.20

Day

-0.20

POSITIVE LOGITS

ime

0.35

fall

0.34

cap

0.30

clubs

0.28

-time

0.28

mar

0.26

lights

0.24

mares

0.24

mare

0.22

caps

0.22

Activations Density 0.052%

references to "night," particularly in various contexts

No Comments

No Known Activations