INDEX

Explanations

mentions of the word "tomorrow."

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

out

-0.17

uts

-0.16

sess

-0.16

"default

-0.15

aware

-0.14

pery

-0.14

adal

-0.14

ioned

-0.14

etable

-0.14

nh

-0.14

POSITIVE LOGITS

 morning

0.39

 afternoon

0.30

mor

0.25

 night

0.24

Morning

0.24

 evening

0.24

land

0.24

 Morning

0.23

 Ð¶Ðµ

0.21

 mornings

0.20

Activations Density 0.012%

mentions of the word "tomorrow."

No Comments

No Known Activations