INDEX

Explanations

the word "just" in various contexts

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

ught

-0.18

ToFront

-0.16

/umd

-0.15

agus

-0.15

ients

-0.15

opers

-0.15

UGHT

-0.15

jez

-0.14

arker

-0.14

 useClass

-0.14

POSITIVE LOGITS

ly

0.28

ifi

0.26

ifiable

0.24

ifications

0.23

iciary

0.22

ifying

0.21

 rewards

0.21

-right

0.20

 about

0.20

 reward

0.20

Activations Density 0.040%

the word "just" in various contexts

No Comments

No Known Activations