INDEX

Explanations

references to the act of running or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Å¡ti

-0.17

ivement

-0.17

antage

-0.17

-0.16

cy

-0.16

cÃ©

-0.16

mente

-0.16

embre

-0.15

arse

-0.15

 Weinstein

-0.15

POSITIVE LOGITS

nings

0.25

ners

0.25

escape

0.25

nung

0.24

.RunWith

0.23

mage

0.22

aways

0.21

nin

0.21

estone

0.21

ning

0.21

Activations Density 0.085%

references to the act of running or related terms

No Comments

No Known Activations