INDEX

Explanations

references to magazine issues and publication details

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

ovel

-0.15

Scr

-0.14

ange

-0.14

ast

-0.14

Ess

-0.14

Presenter

-0.14

 cater

-0.14

 posts

-0.13

 posting

-0.13

.sun

-0.13

POSITIVE LOGITS

 magazine

0.16

egin

0.15

ccione

0.15

Ø§Ø²ÙĦ

0.15

emiz

0.14

 issue

0.14

issue

0.14

è§ĦåĪĴ

0.14

elper

0.14

jur

0.14

Activations Density 0.072%

references to magazine issues and publication details

No Comments

No Known Activations