INDEX

Explanations

technical jargon related to measurements and statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

vos

-0.15

 metrics

-0.14

 Alabama

-0.14

 Marcos

-0.13

Narr

-0.13

monds

-0.13

 Barnett

-0.13

 Patterson

-0.13

à¸Ńà¸ĩ

-0.13

inas

-0.12

POSITIVE LOGITS

 Vintage

0.27

Vintage

0.23

 Sporting

0.20

 Antique

0.18

 vintage

0.18

 antique

0.17

 sporting

0.16

 UNESCO

0.16

Obsolete

0.15

 FIFA

0.15

Activations Density 0.003%

technical jargon related to measurements and statistical analysis

No Comments

No Known Activations