INDEX

Explanations

punctuation marks, specifically commas

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

imu

-0.15

atch

-0.14

æ´¥

-0.14

 fÃ©

-0.14

íĴ

-0.13

 âĹĦ

-0.13

ambi

-0.13

Ø¬Ø§

-0.13

quin

-0.13

arger

-0.13

POSITIVE LOGITS

while

0.23

including

0.21

 while

0.21

 including

0.21

 whether

0.20

such

0.19

 such

0.19

whether

0.18

 whilst

0.18

Including

0.18

Activations Density 0.285%

punctuation marks, specifically commas

No Comments

No Known Activations