INDEX

Explanations

measurements and dimensions of objects or entities

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

 libertin

-0.15

esson

-0.15

 chorus

-0.14

utos

-0.14

teri

-0.14

-than

-0.13

 Emmy

-0.13

Tro

-0.13

 Tiny

-0.13

POSITIVE LOGITS

 wide

0.40

 tall

0.38

 thick

0.34

 long

0.32

 high

0.31

wide

0.31

 deep

0.29

 strong

0.28

-wide

0.27

Wide

0.25

Activations Density 0.045%

measurements and dimensions of objects or entities

No Comments

No Known Activations