INDEX

Explanations

mentions of alcohol consumption and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 feeder

-0.16

olini

-0.16

 Breakfast

-0.15

 hungry

-0.15

 Candy

-0.15

 bake

-0.15

 Bath

-0.15

 Bake

-0.14

 Soap

-0.14

Chocolate

-0.14

POSITIVE LOGITS

 alcohol

0.49

éħĴ

0.46

 alcoholic

0.43

 Alcohol

0.42

 drink

0.41

 Ð°Ð»ÐºÐ¾Ð³

0.39

 rÆ°á»£u

0.38

 booze

0.38

 beer

0.37

cohol

0.37

Activations Density 0.512%

mentions of alcohol consumption and its implications

No Comments

No Known Activations