INDEX

Explanations

key terms related to hospitality and accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÑģÐ¾Ð»

-0.16

podob

-0.15

semb

-0.15

addtogroup

-0.15

inee

-0.15

ACITY

-0.14

Ã¦k

-0.14

ł

-0.14

ARGER

-0.14

.handleClick

-0.14

POSITIVE LOGITS

 Leonard

0.17

leon

0.15

adil

0.15

uan

0.15

Leon

0.15

avel

0.14

iren

0.14

imer

0.14

åħ·

0.14

âĳ

0.13

Activations Density 0.065%

key terms related to hospitality and accommodations

No Comments

No Known Activations