INDEX

Explanations

attributes related to user-friendliness and ease of use in software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Adler

-0.15

bit

-0.15

emon

-0.15

inky

-0.14

ocha

-0.14

ãĥ³ãĥĨ

-0.14

idor

-0.14

inta

-0.14

wyn

-0.14

éĵ¾

-0.14

POSITIVE LOGITS

 interface

0.17

-interface

0.16

 simplicity

0.16

 Interface

0.15

íĿ

0.15

interface

0.14

/simple

0.14

 simples

0.14

-simple

0.14

assen

0.14

Activations Density 0.077%

attributes related to user-friendliness and ease of use in software

No Comments

No Known Activations