INDEX

Explanations

references to fields or areas of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

rgan

-0.16

timeofday

-0.15

illin

-0.15

Ä±lÄ±m

-0.14

itudes

-0.14

icense

-0.14

ancode

-0.14

Vit

-0.14

isin

-0.14

OLUTE

-0.14

POSITIVE LOGITS

trip

0.28

 trip

0.24

 trips

0.23

work

0.23

 Marshal

0.21

ing

0.21

 Trip

0.21

 hockey

0.20

marshal

0.20

Trip

0.20

Activations Density 0.011%

references to fields or areas of study

No Comments

No Known Activations