INDEX

Explanations

references to polls or polling related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ousse

-0.17

íļĮ

-0.17

ements

-0.16

icol

-0.16

esen

-0.16

DefaultCellStyle

-0.15

osity

-0.15

anness

-0.15

essen

-0.15

oby

-0.15

POSITIVE LOGITS

uting

0.33

ution

0.30

uted

0.28

uters

0.28

uter

0.27

ute

0.26

inator

0.26

ster

0.24

ination

0.24

ard

0.22

Activations Density 0.009%

references to polls or polling related topics

No Comments

No Known Activations