INDEX

Explanations

words related to hotel chains and properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

hiba

-0.20

attles

-0.17

unal

-0.16

itals

-0.16

Ð»Ñı

-0.16

stants

-0.15

ìĸ¼

-0.15

-validator

-0.14

OOM

-0.14

ennen

-0.14

POSITIVE LOGITS

 Cald

0.17

bane

0.16

-haspopup

0.16

åĽ£

0.16

 Monkey

0.16

 ÐļÐ°Ð»

0.15

Cal

0.15

duct

0.15

æŀĿ

0.15

Kal

0.15

Activations Density 0.085%

words related to hotel chains and properties

No Comments

No Known Activations