INDEX

Explanations

questions that begin with "which."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

sson

-0.17

loff

-0.15

loid

-0.15

ict

-0.15

egg

-0.15

stuff

-0.14

erva

-0.14

ran

-0.14

ust

-0.14

udiantes

-0.14

POSITIVE LOGITS

soever

0.37

-ever

0.28

 direction

0.26

 ones

0.25

/how

0.24

 Wich

0.23

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

0.21

 among

0.21

-direction

0.20

among

0.20

Activations Density 0.030%

questions that begin with "which."

No Comments

No Known Activations