INDEX

Explanations

numbers and numerical data associated with years or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

sthrough

-0.16

NEL

-0.16

through

-0.16

 through

-0.15

Through

-0.15

STRU

-0.15

 Through

-0.15

Î±ÏģÎ¬

-0.15

orning

-0.15

contri

-0.14

POSITIVE LOGITS

0.25

å¹´

0.22

er

0.21

ëħĦ

0.20

ff

0.19

eko

0.18

Ø

0.18

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.17

–

0.17

 tarihli

0.16

Activations Density 0.049%

numbers and numerical data associated with years or quantities

No Comments

No Known Activations