INDEX

Explanations

punctuation marks and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ãģ§ãģĤ

-0.15

du

-0.14

à¸Ļà¸ķ

-0.14

 port

-0.13

ãģŁãģı

-0.13

åŃĺäºİ

-0.13

.RunWith

-0.13

Py

-0.13

 Bomb

-0.13

vvm

-0.13

POSITIVE LOGITS

let

0.23

So

0.22

Let

0.21

OK

0.21

tl

0.21

Bear

0.20

(I

0.19

So

0.19

(By

0.19

(ok

0.18

Activations Density 0.352%

punctuation marks and their variations

No Comments

No Known Activations