INDEX

Explanations

key geographical locations and their connections to events or actions

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

ofs

-0.17

ije

-0.16

ë¡Ŀ

-0.16

åķı

-0.15

ahoma

-0.15

ombo

-0.15

relude

-0.14

urrences

-0.14

 useForm

-0.14

enguin

-0.14

POSITIVE LOGITS

NEL

0.16

fet

0.16

nier

0.15

 convenience

0.15

etty

0.15

ãĥ»ãĤ¢

0.15

Lub

0.14

estr

0.14

rub

0.14

Rub

0.14

Activations Density 0.259%

key geographical locations and their connections to events or actions

No Comments

No Known Activations