INDEX

Explanations

terms related to cryptography and encryption systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

obe

-0.17

ä¸ģ

-0.16

anni

-0.15

usta

-0.14

erging

-0.14

RON

-0.14

ron

-0.14

 dereg

-0.13

utures

-0.13

POSITIVE LOGITS

 code

0.32

 decrypt

0.29

 decryption

0.28

 ciphertext

0.27

-code

0.27

decrypt

0.27

 codes

0.25

 encrypt

0.25

 Code

0.24

code

0.24

Activations Density 0.049%

terms related to cryptography and encryption systems

No Comments

No Known Activations