INDEX

Explanations

punctuation marks, specifically 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

“

-0.17

 (“

-0.17

 “[

-0.17

‘

-0.17

âĢŀV

-0.16

âĢŀM

-0.16

Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

-0.15

âĢŀN

-0.15

“Oh

-0.14

âĢŀJ

-0.14

POSITIVE LOGITS

 said

0.48

said

0.35

 says

0.33

 explained

0.24

 according

0.24

ÂĿ

0.24

say

0.23

says

0.23

 ÑģÐºÐ°Ð·Ð°Ð»

0.23

 wrote

0.22

Activations Density 0.081%

punctuation marks, specifically quotation marks

No Comments

No Known Activations