INDEX

Explanations

references to historical texts and academic publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

isol

-0.16

.Virtual

-0.15

 Minh

-0.14

/star

-0.14

enko

-0.13

pek

-0.13

.scalablytyped

-0.13

 imports

-0.13

_NR

-0.13

JB

-0.13

POSITIVE LOGITS

 volume

0.33

 volumes

0.32

 Volume

0.31

-volume

0.31

Volume

0.29

volume

0.27

olume

0.25

å·»

0.24

Volumes

0.23

.volume

0.23

Activations Density 0.053%

references to historical texts and academic publications

No Comments

No Known Activations