INDEX

Explanations

terms related to entropy and thermodynamic equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-rad

-0.15

é¡

-0.15

 é¡

-0.14

 èĹ

-0.14

 Radical

-0.14

angles

-0.13

ÙĪØ¨ÛĮ

-0.13

DDL

-0.13

_usr

-0.13

POSITIVE LOGITS

 entropy

0.26

Entropy

0.24

 heat

0.23

 Heat

0.23

entropy

0.23

çĨ±

0.22

 therm

0.22

heat

0.21

çĥŃ

0.21

Heat

0.21

Activations Density 0.031%

terms related to entropy and thermodynamic equations

No Comments

No Known Activations