INDEX

Explanations

references to wine and related experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Brew

-0.15

 Coffee

-0.15

antan

-0.15

 ØªØ£

-0.15

íĸ

-0.14

ì§ĵ

-0.14

pecies

-0.14

elow

-0.14

 Cash

-0.14

 feed

-0.14

POSITIVE LOGITS

 wine

0.31

 wines

0.30

 Wine

0.26

vin

0.22

 bottle

0.22

wine

0.22

 bottles

0.21

 vine

0.20

 tasting

0.20

 grapes

0.20

Activations Density 0.153%

references to wine and related experiences

No Comments

No Known Activations