INDEX

Explanations

terms related to skincare and hair treatment products

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

/tos

-0.15

/animate

-0.15

inement

-0.15

 Thomson

-0.14

morgan

-0.14

 steward

-0.14

allo

-0.13

 Thá»ĭ

-0.13

ifton

-0.13

unate

-0.13

POSITIVE LOGITS

ep

0.33

ker

0.27

Ep

0.25

seb

0.24

 horny

0.24

(ep

0.23

der

0.23

 cells

0.22

Ker

0.21

 barrier

0.21

Activations Density 0.017%

terms related to skincare and hair treatment products

No Comments

No Known Activations