INDEX

Explanations

terms related to data analysis and analytics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 laundry

-0.15

Mej

-0.15

ç½²

-0.14

ãģķãĤī

-0.14

 ÙĨØŃ

-0.14

gue

-0.14

ruh

-0.14

uther

-0.14

kees

-0.14

dek

-0.14

POSITIVE LOGITS

andon

0.15

 GetString

0.14

club

0.14

uang

0.13

 engine

0.13

ires

0.13

 Diamonds

0.13

 Gems

0.13

 Engines

0.13

à¸Ńà¸Ļà¸Ķ

0.13

Activations Density 0.065%

terms related to data analysis and analytics in various contexts

No Comments

No Known Activations