INDEX

Explanations

requests for assistance or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ð»ÐµÐ¶

-0.18

anian

-0.15

Ð°Ð´Ñĥ

-0.15

zent

-0.15

iesel

-0.15

bum

-0.14

stud

-0.14

 FAQs

-0.14

 Annunci

-0.14

ÙĬÙĤ

-0.14

POSITIVE LOGITS

 please

0.39

please

0.32

 Please

0.30

 PLEASE

0.28

Please

0.28

 tell

0.26

 bitte

0.24

 pleas

0.23

PLEASE

0.22

tell

0.21

Activations Density 0.074%

requests for assistance or information

No Comments

No Known Activations