INDEX

Explanations

technical specifications related to dimensions and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 spherical

-0.17

 stitches

-0.16

 funnel

-0.15

coal

-0.15

aminer

-0.15

 stitching

-0.15

 cone

-0.15

ãģĻãģĻ

-0.14

 tripod

-0.14

 coal

-0.14

POSITIVE LOGITS

 sheets

0.27

.sheet

0.24

 sheet

0.23

 panels

0.23

 strips

0.22

 pieces

0.22

 thickness

0.21

 cuts

0.21

cut

0.21

 Sheets

0.21

Activations Density 0.245%

technical specifications related to dimensions and measurements

No Comments

No Known Activations