INDEX

Explanations

descriptions of property features and their appeal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

_bm

-0.17

SHA

-0.15

usher

-0.15

 doors

-0.15

 Lect

-0.15

Overrides

-0.14

å¶

-0.14

 Modal

-0.13

POSITIVE LOGITS

 backyard

0.41

 garden

0.40

 yard

0.40

 Yard

0.32

-yard

0.32

 gardens

0.31

yard

0.29

 yards

0.29

 courtyard

0.28

åºŃ

0.28

Activations Density 0.218%

descriptions of property features and their appeal

No Comments

No Known Activations