INDEX

Explanations

discussions related to workshops and educational conferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ccione

-0.16

ingu

-0.15

urai

-0.14

PEND

-0.14

itest

-0.14

Ð»Ð°Ñĩ

-0.14

trim

-0.14

insk

-0.14

uars

-0.13

 trim

-0.13

POSITIVE LOGITS

 Madden

0.15

SWG

0.15

byname

0.15

armor

0.14

kest

0.14

ByID

0.14

 Handler

0.14

acket

0.14

 Commod

0.13

ackets

0.13

Activations Density 0.097%

discussions related to workshops and educational conferences

No Comments

No Known Activations