INDEX

Explanations

adjectives and adverbs that express varying degrees of intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Very

-0.20

Very

-0.17

ugh

-0.17

 Extremely

-0.15

 very

-0.15

anggan

-0.15

VERY

-0.15

ullo

-0.15

Î¸Î·

-0.15

very

-0.14

POSITIVE LOGITS

 strong

0.26

 close

0.25

 large

0.25

 loud

0.24

 fast

0.23

 tall

0.23

 important

0.22

big

0.22

 popular

0.22

close

0.21

Activations Density 0.505%

adjectives and adverbs that express varying degrees of intensity

No Comments

No Known Activations