INDEX

Explanations

terms related to specific industries or sectors

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

nings

-0.18

velt

-0.18

gos

-0.17

ãĥ«ãĥī

-0.16

ogany

-0.15

joy

-0.15

faction

-0.15

aign

-0.14

erto

-0.14

veau

-0.14

POSITIVE LOGITS

ial

0.44

al

0.39

ialized

0.26

ally

0.25

IAL

0.24

ual

0.23

alist

0.23

arium

0.22

ized

0.21

-wide

0.21

Activations Density 0.018%

terms related to specific industries or sectors

No Comments

No Known Activations