INDEX

Explanations

information related to tourist attractions and passes

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

AKE

-0.17

uracy

-0.15

 marshaller

-0.15

/tiny

-0.14

ìŀ¡ëĭ´

-0.14

AGON

-0.14

 Kens

-0.14

 compensated

-0.14

 niche

-0.13

oen

-0.13

POSITIVE LOGITS

 card

0.27

 passes

0.27

 pass

0.26

 validity

0.25

 cards

0.24

passes

0.24

-card

0.23

 valid

0.23

 Card

0.21

card

0.21

Activations Density 0.055%

information related to tourist attractions and passes

No Comments

No Known Activations