INDEX

Explanations

terms related to technology and software systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

DeV

-0.16

isons

-0.15

éģ

-0.15

Bug

-0.15

æģ¯

-0.14

atha

-0.14

clipse

-0.14

ificio

-0.14

ãģĭãģĳ

-0.14

pora

-0.14

POSITIVE LOGITS

 rack

0.34

 Rack

0.32

 blade

0.31

 server

0.30

 servers

0.29

 Blade

0.29

 Blades

0.29

 blades

0.29

 Servers

0.26

server

0.26

Activations Density 0.018%

terms related to technology and software systems

No Comments

No Known Activations