INDEX

Explanations

products associated with cleaning and maintenance tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 refriger

-0.15

_smooth

-0.15

Smooth

-0.15

smooth

-0.14

ummer

-0.14

urv

-0.14

_READY

-0.13

 Smash

-0.13

 chop

-0.13

POSITIVE LOGITS

 cleaning

0.46

 Cleaning

0.44

Cleaning

0.36

 cleaners

0.35

 cleaned

0.34

 cleans

0.31

 cleaner

0.30

.clean

0.29

clean

0.29

 Cleaner

0.29

Activations Density 0.215%

products associated with cleaning and maintenance tasks

No Comments

No Known Activations