INDEX

Explanations

technical terms and concepts related to encryption and cryptography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

urat

-0.19

imary

-0.16

ternet

-0.15

ÐµÑĢÐµÑĩ

-0.15

ssel

-0.15

elight

-0.15

usty

-0.15

 Ð¿ÐµÑĢÐµÐº

-0.14

ustom

-0.14

éĢ

-0.14

POSITIVE LOGITS

ãĥ¼ãĥª

0.15

 zÃ¡

0.15

à¸£

0.15

iferay

0.14

 Harden

0.14

WindowState

0.14

 mystery

0.14

ba

0.14

gorm

0.14

0.13

Activations Density 0.070%

technical terms and concepts related to encryption and cryptography

No Comments

No Known Activations

technical terms and concepts related to encryption and cryptography

No Comments

No Known Activations