INDEX

Explanations

technology and application-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

avir

-0.14

iges

-0.14

pus

-0.14

 Descriptor

-0.14

 waived

-0.14

ä»ĭ

-0.14

oola

-0.14

allery

-0.13

iveau

-0.13

'gc

-0.13

POSITIVE LOGITS

 Notes

0.28

 notes

0.28

 note

0.24

.notes

0.24

Notes

0.24

notes

0.24

-notes

0.23

 Note

0.22

 organizer

0.22

Note

0.22

Activations Density 0.185%

technology and application-related terminology

No Comments

No Known Activations