INDEX

Explanations

geographic locations and names associated with events

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

åºŃ

-0.16

ocracy

-0.16

çłĤ

-0.14

azÄ±

-0.14

 Merry

-0.14

emics

-0.13

 Kamp

-0.13

ojÃŃ

-0.13

Ø§Ø¯Ùĩ

-0.13

-sdk

-0.13

POSITIVE LOGITS

anon

0.17

antino

0.16

imb

0.16

0.15

 Nath

0.15

berman

0.15

enton

0.15

colm

0.15

burg

0.15

jad

0.15

Activations Density 0.098%

geographic locations and names associated with events

No Comments

No Known Activations