INDEX

Explanations

references to tourism and tourist-related concepts

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

oust

-0.18

ÅŁk

-0.15

haft

-0.15

nings

-0.15

nie

-0.15

hrd

-0.14

cors

-0.14

sv

-0.14

ities

-0.14

ings

-0.14

POSITIVE LOGITS

 attractions

0.26

 attraction

0.25

 Attr

0.24

attr

0.20

 destination

0.18

 traps

0.18

 destinations

0.18

 trap

0.17

.attr

0.17

 attr

0.16

Activations Density 0.013%

references to tourism and tourist-related concepts

No Comments

No Known Activations