INDEX

Explanations

keywords related to reporting and news

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

utches

-0.14

ÙĬÙĪ

-0.14

 Manga

-0.13

------+------+

-0.13

.BLL

-0.13

Ð°ÑĢÐ°Ð¼

-0.13

POR

-0.13

akespeare

-0.13

NegativeButton

-0.13

ÙĩØ±

-0.13

POSITIVE LOGITS

Ey

0.32

WX

0.32

 meteor

0.31

FOX

0.30

 Channel

0.29

CBS

0.29

 Meteor

0.28

WB

0.28

 anchors

0.28

 station

0.27

Activations Density 0.091%

keywords related to reporting and news

No Comments

No Known Activations