INDEX

Explanations

indicators of deception and fraudulent activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ãģŁãģı

-0.17

ansi

-0.17

elez

-0.15

á»ķ

-0.15

aphrag

-0.15

.Contracts

-0.15

 Ð¼Ð¸Ð»

-0.15

Ñĵ

-0.14

istrovstvÃŃ

-0.14

ansÄ±

-0.14

POSITIVE LOGITS

Pon

0.23

MLM

0.23

 affiliates

0.22

ML

0.20

 affiliate

0.20

/py

0.19

 pyramid

0.19

 securities

0.19

affiliate

0.18

ml

0.17

Activations Density 0.001%

indicators of deception and fraudulent activities

No Comments

No Known Activations