INDEX

Explanations

occurrences of the word "all" and associated class or category references in a structured format

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

atch

-0.16

fac

-0.15

eut

-0.15

yped

-0.15

unp

-0.15

ãģ«ãģ¤

-0.15

ontent

-0.15

ATCH

-0.14

resa

-0.14

POSITIVE LOGITS

classes

0.24

 Classes

0.24

Classes

0.23

 classes

0.22

_classes

0.19

(classes

0.17

/classes

0.16

 clases

0.16

.classes

0.16

skins

0.16

Activations Density 0.011%

occurrences of the word "all" and associated class or category references in a structured format

No Comments

No Known Activations