INDEX

Explanations

references to 'rocket' and 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

elijk

-0.17

ifton

-0.16

lus

-0.15

.Inf

-0.15

iche

-0.14

à¸¥à¸²à¸Ķ

-0.14

ÙĥØ©

-0.14

yntax

-0.14

licant

-0.14

 Robotics

-0.14

POSITIVE LOGITS

ry

0.34

tes

0.30

eer

0.29

ting

0.25

-powered

0.21

te

0.21

Powered

0.21

-prop

0.20

raman

0.20

Activations Density 0.007%

references to 'rocket' and related terms

No Comments

No Known Activations