INDEX

Explanations

statements about companies' capabilities and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ulos

-0.15

IGGER

-0.14

 Trap

-0.14

itten

-0.14

igan

-0.14

gia

-0.14

 trap

-0.13

éĤ¦

-0.13

 Works

-0.13

ÑĥÑĪ

-0.13

POSITIVE LOGITS

 uniquely

0.36

 equipped

0.34

 qualified

0.33

-equipped

0.30

 equip

0.29

qualified

0.28

-position

0.28

 Qualified

0.27

 positioned

0.26

 ideally

0.25

Activations Density 0.116%

statements about companies' capabilities and qualifications

No Comments

No Known Activations