INDEX

Explanations

advice related to health, safety, and preventive measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

aira

-0.15

enco

-0.14

 orderly

-0.14

ÅŁam

-0.14

 discreet

-0.13

ayd

-0.13

_dropout

-0.13

è³¢

-0.13

 humble

-0.13

 appropriate

-0.13

POSITIVE LOGITS

 unless

0.39

unless

0.33

Unless

0.30

 Unless

0.29

 anything

0.24

ANY

0.24

 temptation

0.24

 EVER

0.24

too

0.23

ä»»ä½ķ

0.22

Activations Density 0.356%

advice related to health, safety, and preventive measures

No Comments

No Known Activations