INDEX

Explanations

references to technology and media platforms, particularly in the context of digital content consumption

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

orra

-0.17

orro

-0.17

erner

-0.15

piry

-0.15

erek

-0.15

venes

-0.15

usto

-0.14

ork

-0.14

orado

-0.14

POSITIVE LOGITS

 anyway

0.79

Anyway

0.66

 anyways

0.65

 Anyway

0.63

 anyhow

0.54

 atleast

0.31

 toch

0.27

 jeden

0.26

 least

0.25

least

0.24

Activations Density 0.173%

references to technology and media platforms, particularly in the context of digital content consumption

No Comments

No Known Activations