INDEX

Explanations

punctuation marks, particularly commas and quotation marks

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

’e

-0.17

 “[

-0.17

’ÑĹ

-0.15

‘

-0.15

“

-0.15

“Oh

-0.15

 (“

-0.15

âĢŀM

-0.14

âĢŀV

-0.14

âĢŀN

-0.14

POSITIVE LOGITS

 says

0.29

 said

0.27

ÂĿ

0.25

 reads

0.24

 read

0.22

say

0.21

he

0.20

 according

0.19

says

0.19

 wrote

0.19

Activations Density 0.108%

punctuation marks, particularly commas and quotation marks

No Comments

No Known Activations