INDEX

Explanations

financial terminology related to fees and credit

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

omik

-0.16

ameda

-0.16

ibri

-0.16

.opensource

-0.15

Ã´m

-0.15

umpt

-0.15

irie

-0.14

 pension

-0.14

orna

-0.14

clid

-0.14

POSITIVE LOGITS

 card

0.37

 cards

0.35

 Card

0.32

 Cards

0.29

Cards

0.29

 CARD

0.29

cards

0.27

CARD

0.26

-card

0.26

card

0.26

Activations Density 0.012%

financial terminology related to fees and credit

No Comments

No Known Activations