INDEX

Explanations

punctuation marks and formatting symbols in text

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

>:</

-0.18

>Main

-0.16

imbabwe

-0.15

_ORIENTATION

-0.15

arb

-0.15

><?=$

-0.15

orra

-0.14

ringe

-0.14

>Nama

-0.14

Ð°ÑĢÑĩ

-0.14

POSITIVE LOGITS

0.46

>manual

0.33

 >↵

0.31

>↵

0.29

>equals

0.29

>NN

0.29

>>

0.28

>,

0.26

>-

0.26

Activations Density 0.171%

punctuation marks and formatting symbols in text

No Comments

No Known Activations

punctuation marks and formatting symbols in text

No Comments

No Known Activations