INDEX

Explanations

occurrences of the word "Sit" and its variations, suggesting a focus on unique contexts or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

eer

-0.19

clid

-0.18

acias

-0.17

edException

-0.17

erged

-0.16

alary

-0.16

eded

-0.16

iye

-0.16

ÐµÐ¿ÑĤÐ¸

-0.16

bedo

-0.15

POSITIVE LOGITS

uated

0.37

uate

0.34

uation

0.31

uating

0.30

uations

0.28

-down

0.23

 amet

0.23

ooter

0.23

izens

0.22

down

0.21

Activations Density 0.008%

occurrences of the word "Sit" and its variations, suggesting a focus on unique contexts or settings

No Comments

No Known Activations