INDEX

Explanations

variations of the word "Fab" and its related forms, suggesting a focus on brand or product significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ying

-0.16

Ã¦kke

-0.16

enden

-0.15

eed

-0.14

elry

-0.14

etik

-0.14

itt

-0.14

cker

-0.14

à¸©

-0.14

stice

-0.14

POSITIVE LOGITS

ulous

0.40

ulously

0.36

rics

0.28

rique

0.25

rika

0.24

erge

0.24

rik

0.24

rice

0.23

ulist

0.22

RIC

0.22

Activations Density 0.009%

variations of the word "Fab" and its related forms, suggesting a focus on brand or product significance

No Comments

No Known Activations