INDEX

Explanations

content related to user authentication and status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

holm

-0.17

_PROC

-0.15

ÑĥÐ·

-0.15

Vir

-0.14

agen

-0.14

Äįin

-0.14

ÑĥÐµÑĤ

-0.14

attern

-0.13

 baseUrl

-0.13

 splitting

-0.13

POSITIVE LOGITS

 logged

0.26

 session

0.20

 logout

0.20

 login

0.20

0.19

session

0.19

 sess

0.18

 Logout

0.18

logged

0.18

 Logged

0.17

Activations Density 0.115%

content related to user authentication and status

No Comments

No Known Activations