INDEX

Explanations

attributes related to user interface design and usability

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

 vulnerability

-0.15

 justice

-0.15

rup

-0.15

à¸§à¸¥

-0.15

zee

-0.13

smarty

-0.13

abaj

-0.13

 hostage

-0.13

chain

-0.12

/moment

-0.12

POSITIVE LOGITS

 interface

0.43

UI

0.43

 Interface

0.39

UI

0.37

ui

0.37

 interfaces

0.36

Interface

0.35

interface

0.35

-interface

0.35

ui

0.34

Activations Density 0.277%

attributes related to user interface design and usability

No Comments

No Known Activations