INDEX

Explanations

references to deceptive practices and malicious activities in digital communications

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

Insensitive

-0.15

quila

-0.14

^K

-0.14

DFS

-0.14

ichtet

-0.13

PÅĻi

-0.13

Ð¾Ð¼ÐµÑĢ

-0.13

opyright

-0.13

eldorf

-0.13

POSITIVE LOGITS

 trick

0.43

mas

0.40

 deception

0.37

 tricks

0.37

 Trick

0.35

 Tricks

0.35

 deceive

0.35

 fool

0.34

 deceptive

0.34

 dece

0.34

Activations Density 0.393%

references to deceptive practices and malicious activities in digital communications

No Comments

No Known Activations