INDEX

Explanations

references to various media production types and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.datasource

-0.16

ogl

-0.15

isposable

-0.15

ican

-0.15

voc

-0.15

iasm

-0.14

dlg

-0.14

uly

-0.14

ega

-0.13

 rude

-0.13

POSITIVE LOGITS

 clients

0.26

 corporate

0.24

 Clients

0.24

 client

0.23

 commercials

0.22

 commercial

0.21

Clients

0.21

clients

0.20

 Corporate

0.20

å®¢æĪ·

0.20

Activations Density 0.124%

references to various media production types and activities

No Comments

No Known Activations