INDEX

Explanations

elements related to hotel features and amenities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Stam

-0.17

obel

-0.16

vette

-0.15

ollo

-0.15

inqu

-0.14

_INF

-0.14

Î¯ÏīÎ½

-0.14

 kelim

-0.14

 compound

-0.14

licted

-0.13

POSITIVE LOGITS

IH

0.16

ardon

0.15

 universities

0.14

 plag

0.14

IH

0.14

Î»Î¹Î¬

0.14

AccessException

0.14

icone

0.14

ussen

0.14

pet

0.14

Activations Density 0.034%

elements related to hotel features and amenities

No Comments

No Known Activations