INDEX

Explanations

mentions of specific product features and benefits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 collateral

-0.15

 mouseX

-0.15

hab

-0.14

æ²Ļ

-0.14

ritis

-0.14

 Ø´Ùģ

-0.14

upy

-0.14

/browser

-0.14

 tranquil

-0.14

 Jacket

-0.14

POSITIVE LOGITS

 absorb

0.29

 Inserts

0.24

 dispos

0.23

 inserts

0.23

 absorption

0.21

 Cloth

0.20

Abs

0.20

 insert

0.20

 disposable

0.20

 diapers

0.20

Activations Density 0.020%

mentions of specific product features and benefits

No Comments

No Known Activations