INDEX

Explanations

keywords related to film awards and nominations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lou

-0.15

-0.14

 ÑĥÑĩÐ°ÑģÑĤ

-0.14

aten

-0.14

 Wander

-0.14

imb

-0.14

gun

-0.14

con

-0.14

qr

-0.13

rab

-0.13

POSITIVE LOGITS

 Editing

0.19

editing

0.18

0.17

 picture

0.17

 foreign

0.17

 editing

0.17

 original

0.17

pollo

0.16

 Supporting

0.16

ÐµÐºÑĥ

0.16

Activations Density 0.013%

keywords related to film awards and nominations

No Comments

No Known Activations