INDEX

Explanations

names associated with various individuals and noteworthy appearances or roles in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

anguage

-0.15

ody

-0.15

ãģ°

-0.15

/UIKit

-0.15

recision

-0.14

pus

-0.14

backs

-0.14

enton

-0.14

incinn

-0.14

ÛĮ

-0.14

POSITIVE LOGITS

apo

0.19

 trÃŃ

0.15

ê¸Ī

0.15

0.14

CRY

0.14

 Kelley

0.14

AVA

0.14

0.13

TextStyle

0.13

 bent

0.13

Activations Density 0.805%

names associated with various individuals and noteworthy appearances or roles in media

No Comments

No Known Activations