INDEX

Explanations

elements related to tourism and entertainment destinations

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

odor

-0.17

buch

-0.17

ograms

-0.17

ward

-0.15

 hypoth

-0.14

skip

-0.14

worth

-0.14

ogram

-0.14

/Branch

-0.14

-wide

-0.13

POSITIVE LOGITS

hub

0.26

 district

0.23

 center

0.23

 zone

0.22

 centre

0.21

Hub

0.21

 hubs

0.20

district

0.20

 scene

0.20

hub

0.20

Activations Density 0.141%

elements related to tourism and entertainment destinations

No Comments

No Known Activations