INDEX

Explanations

references to security screening and travel-related protocols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iye

-0.16

bsolute

-0.16

è£Ĥ

-0.15

ensus

-0.14

oice

-0.14

hod

-0.14

çĴ

-0.14

ertia

-0.14

burn

-0.13

tryside

-0.13

POSITIVE LOGITS

 screening

0.31

 airport

0.30

 screenings

0.29

TSA

0.28

 Screening

0.28

 Airport

0.28

airport

0.27

 checkpoint

0.25

 airports

0.25

Airport

0.24

Activations Density 0.049%

references to security screening and travel-related protocols

No Comments

No Known Activations