INDEX

Explanations

forms of the verb "to be" in various tenses

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

ton

-0.19

Ð½Ð¸ÑĨÑĮ

-0.16

aro

-0.16

ption

-0.16

agic

-0.15

ucht

-0.15

gence

-0.14

eking

-0.14

tons

-0.14

dorf

-0.14

POSITIVE LOGITS

 supposed

0.34

/is

0.30

/w

0.28

/how

0.26

/do

0.24

 gonna

0.23

 suppose

0.23

 wont

0.23

 perceived

0.21

 alleged

0.20

Activations Density 0.084%

forms of the verb "to be" in various tenses

No Comments

No Known Activations