INDEX

Explanations

references to scams 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 @ 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

spy

-0.16

ennis

-0.15

CSR

-0.14

iances

-0.14

lobby

-0.14

Ã³g

-0.14

æ´

-0.14

 Hakk

-0.14

 smugg

-0.14

PCODE

-0.14

POSITIVE LOGITS

 scams

0.34

 scheme

0.33

 scam

0.33

Pon

0.32

 schemes

0.32

 victims

0.29

scheme

0.28

 victim

0.27

 Scheme

0.27

Scheme

0.27

Activations Density 0.128%

references to scams and fraudulent activities

No Comments

No Known Activations