INDEX

Explanations

punctuation marks and special characters used in writing or dialogue

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

âĸį

-0.17

 Â©

-0.15

tags

-0.14

ï»¿#

-0.14

ëį°ìĿ´íĬ¸

-0.13

category

-0.13

Tags

-0.12

à¸¡à¸Ļà¸ķà¸£

-0.12

ìĨĮê°ľ

-0.12

 onCancelled

-0.12

POSITIVE LOGITS

agree

0.27

 Agree

0.23

 agreed

0.23

Ag

0.23

 agree

0.22

Ag

0.21

/ag

0.21

 exactly

0.21

 Ping

0.20

amen

0.19

Activations Density 0.118%

punctuation marks and special characters used in writing or dialogue

No Comments

No Known Activations