INDEX

Explanations

various forms of media titles and associated metrics or ratings

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

ardu

-0.15

.ops

-0.15

fir

-0.15

Yar

-0.15

 Fried

-0.14

ied

-0.14

uru

-0.14

edback

-0.14

esan

-0.14

iosis

-0.14

POSITIVE LOGITS

ataire

0.17

ento

0.16

dzi

0.16

Yue

0.16

ICH

0.15

Ell

0.14

//****************************************************************

0.13

tml

0.13

flare

0.13

Activations Density 0.025%

various forms of media titles and associated metrics or ratings

No Comments

No Known Activations