INDEX

Explanations

instances of the word "IN" indicating location or inclusion

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

EMPLARY

-0.17

led

-0.16

anmar

-0.15

Ø¨Ø§ÙĦ

-0.15

bean

-0.15

ÑĪÐ¸Ð½

-0.15

aways

-0.15

ingly

-0.15

plied

-0.15

ily

-0.14

POSITIVE LOGITS

vest

0.27

ventory

0.23

formation

0.23

structions

0.22

crement

0.22

nov

0.22

NO

0.21

tÃ©

0.21

TEGR

0.21

TEL

0.21

Activations Density 0.010%

instances of the word "IN" indicating location or inclusion

No Comments

No Known Activations

instances of the word "IN" indicating location or inclusion

No Comments

No Known Activations