INDEX

Explanations

the use of the verb "to be" in various forms

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

å®ĥ

-0.20

ä¸Ģä¸ª

-0.18

It

-0.17

çļĦä¸Ģä¸ª

-0.17

osi

-0.17

ä¸Ģä¸ªäºº

-0.16

Anything

-0.16

ä¸ĢåĢĭ

-0.15

 Anything

-0.15

(it

-0.15

POSITIVE LOGITS

 they

0.28

we

0.26

 these

0.25

/w

0.25

 those

0.23

tha

0.22

nt

0.21

 Ð¾Ð½Ð¸

0.20

ady

0.20

/is

0.19

Activations Density 0.043%

the use of the verb "to be" in various forms

No Comments

No Known Activations