INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Nights

-0.21

 evenings

-0.18

 nights

-0.18

 NIGHT

-0.16

Tonight

-0.16

 night

-0.16

 Night

-0.15

 taÅŁ

-0.15

_ALWAYS

-0.15

 evening

-0.15

POSITIVE LOGITS

 morning

0.30

Morning

0.29

 mornings

0.28

 Morning

0.28

 breakfast

0.28

 Breakfast

0.23

 Wake

0.23

 wake

0.22

Wake

0.22

 dawn

0.22

Activations Density 0.033%

No Comments

No Known Activations