INDEX

Explanations

references to applications and information related to technology and resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

edReader

-0.23

een

-0.22

aire

-0.20

IZED

-0.20

ized

-0.20

naires

-0.19

hips

-0.19

hood

-0.19

ered

-0.19

eer

-0.19

POSITIVE LOGITS

ios

0.20

istory

0.19

Ùĳ

0.19

uation

0.19

imize

0.19

ut

0.19

ug

0.18

otr

0.18

Ã©ro

0.18

ere

0.18

Activations Density 0.624%

references to applications and information related to technology and resources

No Comments

No Known Activations