INDEX

Explanations

discussions about publishing and self-publishing in literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Ð¿ÐµÑĢÐµÐ¿Ð¸Ñģ

-0.14

apur

-0.14

GLE

-0.14

ÏĦÎ¿Î½

-0.14

ÑģÑĭÐ»

-0.14

ÑĥÐ¼Ð¾Ð²

-0.14

oteca

-0.14

.scalablytyped

-0.13

_fault

-0.13

ordo

-0.13

POSITIVE LOGITS

 self

0.36

 Self

0.31

 indie

0.28

self

0.28

POD

0.27

Self

0.26

 Indies

0.25

 SELF

0.24

 vanity

0.24

-self

0.24

Activations Density 0.024%

discussions about publishing and self-publishing in literature

No Comments

No Known Activations