INDEX

Explanations

information related to tourist attractions and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ibraltar

-0.15

 maduras

-0.15

Advertisement

-0.14

ÑĮÑİÑĤ

-0.14

 Wilderness

-0.14

 Nikol

-0.14

.getComponent

-0.14

sterdam

-0.14

inery

-0.14

 somebody

-0.13

POSITIVE LOGITS

 Â«

0.26

 notably

0.22

Â«

0.21

 (Â«

0.18

 recommand

0.18

 VerfÃ¼g

0.17

nal

0.17

Infos

0.16

 upstream

0.16

 lille

0.16

Activations Density 0.811%

information related to tourist attractions and activities

No Comments

No Known Activations