INDEX

Explanations

quantitative descriptions of structures or statistics related to items and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ĥĿ

-0.17

trl

-0.17

shal

-0.15

 vess

-0.15

äºĮäºº

-0.14

Ã¤ch

-0.14

PlainText

-0.14

stants

-0.14

enha

-0.14

à¤¯à¤¨

-0.14

POSITIVE LOGITS

nop

0.15

ibs

0.14

 full

0.14

jam

0.14

 Gerald

0.14

apid

0.14

Anal

0.14

elles

0.13

 static

0.13

 Invest

0.13

Activations Density 0.341%

quantitative descriptions of structures or statistics related to items and measurements

No Comments

No Known Activations