INDEX

Explanations

references to permissions, grants, and official statuses

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

uest

-0.15

enson

-0.15

olah

-0.14

lingen

-0.14

avy

-0.14

Ð´Ð¸

-0.14

 Erotik

-0.14

bt

-0.14

 awakeFromNib

-0.13

awk

-0.13

POSITIVE LOGITS

 permission

0.29

 status

0.24

 full

0.24

 passage

0.24

permission

0.23

 membership

0.22

 custody

0.21

adm

0.21

 admission

0.21

 approval

0.20

Activations Density 0.305%

references to permissions, grants, and official statuses

No Comments

No Known Activations