INDEX

Explanations

references to loss and disappearance

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

ÙĬÙĥÙĬ

-0.16

.scalablytyped

-0.16

zdy

-0.16

unca

-0.15

 Survival

-0.15

-0.14

znÃ¡m

-0.14

llu

-0.14

æļ

-0.14

POSITIVE LOGITS

 gone

0.72

 Gone

0.55

gone

0.54

 dead

0.43

dead

0.33

 extinct

0.33

 Dead

0.32

 DEAD

0.32

 absent

0.30

 deceased

0.29

Activations Density 0.282%

references to loss and disappearance

No Comments

No Known Activations