INDEX

Explanations

terms related to credit, particularly credit cards and credit scores

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

Credits

-0.20

ernaut

-0.19

levard

-0.17

 credited

-0.17

 credits

-0.17

 Rover

-0.17

 Credits

-0.17

credits

-0.16

 creditors

-0.15

 Credit

-0.15

POSITIVE LOGITS

worth

0.34

worthy

0.30

 card

0.28

 union

0.28

 unions

0.25

ors

0.25

-card

0.25

card

0.25

 Union

0.22

 Card

0.22

Activations Density 0.010%

terms related to credit, particularly credit cards and credit scores

No Comments

No Known Activations