INDEX

Explanations

terms associated with travel and tourism

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

voir

-0.15

ugu

-0.15

lez

-0.14

æĴ®

-0.14

ecycle

-0.14

Ã¦re

-0.14

neau

-0.14

 sorumlu

-0.14

stellung

-0.13

loh

-0.13

POSITIVE LOGITS

 looking

0.52

looking

0.45

 Looking

0.39

-looking

0.36

Looking

0.36

 alike

0.34

 seeking

0.32

 LOOK

0.31

 interested

0.31

 wanting

0.30

Activations Density 0.260%

terms associated with travel and tourism

No Comments

No Known Activations