INDEX

Explanations

details about television series, including their ratings and network information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

olor

-0.18

olini

-0.16

astos

-0.14

ilha

-0.14

kÃ³w

-0.14

OME

-0.14

lbrace

-0.14

 KrÃ¡l

-0.14

.Override

-0.14

oneksi

-0.14

POSITIVE LOGITS

 subsidi

0.14

_singular

0.13

 Rivers

0.13

 Walters

0.13

 elems

0.13

.GetSize

0.13

íĹĮ

0.13

dit

0.13

 Secretary

0.13

SWG

0.13

Activations Density 0.049%

details about television series, including their ratings and network information

No Comments

No Known Activations