INDEX

Explanations

calls to action directed at a community or group

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ocker

-0.16

vida

-0.16

soever

-0.15

 Magnet

-0.15

ierce

-0.15

locker

-0.15

 alternatively

-0.14

á

-0.14

 Locker

-0.14

áºŃu

-0.14

POSITIVE LOGITS

hung

0.18

ourcing

0.17

åĮ

0.15

zcze

0.15

Hang

0.15

yang

0.15

ose

0.15

yms

0.15

 Hang

0.15

å¾

0.14

Activations Density 0.565%

calls to action directed at a community or group

No Comments

No Known Activations