INDEX

Explanations

concepts related to automation and public service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oppel

-0.15

Ã¦nd

-0.15

ifetime

-0.14

 Demp

-0.14

.scalablytyped

-0.14

 ZÃ¡p

-0.14

 COLORS

-0.14

datatable

-0.13

riet

-0.13

 skup

-0.13

POSITIVE LOGITS

 partial

0.45

 Partial

0.40

 partially

0.38

Partial

0.36

partial

0.36

 partly

0.31

.partial

0.31

_partial

0.29

éĥ¨åĪĨ

0.28

 parts

0.27

Activations Density 0.202%

concepts related to automation and public service

No Comments

No Known Activations