INDEX

Explanations

punctuation marks and their associated frequencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

asu

-0.15

-in

-0.15

warts

-0.14

 AdemÃ¡s

-0.14

ÙĪÙĨÙĩ

-0.14

rant

-0.13

ataka

-0.13

thur

-0.13

à¸£à¸¡

-0.13

ãĥĲãĤ¹

-0.13

POSITIVE LOGITS

 ÙĪÙģÙĬ

0.25

 During

0.25

 during

0.23

During

0.22

 durante

0.19

during

0.18

On

0.18

At

0.18

In

0.17

 Near

0.16

Activations Density 0.175%

punctuation marks and their associated frequencies

No Comments

No Known Activations