INDEX

Explanations

mentions of network-related concepts and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Networks

-0.28

Network

-0.28

 Network

-0.26

 networks

-0.25

network

-0.24

 Networking

-0.24

 network

-0.24

_network

-0.24

 networking

-0.24

 NETWORK

-0.23

POSITIVE LOGITS

ed

0.51

ted

0.27

ED

0.25

ings

0.24

edBy

0.24

lify

0.24

edImage

0.23

-wide

0.22

wide

0.21

er

0.21

Activations Density 0.031%

mentions of network-related concepts and terminology

No Comments

No Known Activations