INDEX

Explanations

mentions of news organizations and their publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÐµÐ¼Ð¾Ð½

-0.17

NPR

-0.15

elyn

-0.15

aliz

-0.14

_radi

-0.14

 Hlav

-0.14

bbc

-0.14

CBC

-0.13

CNN

-0.13

BBC

-0.13

POSITIVE LOGITS

 newspaper

0.32

 Newspaper

0.26

 newspapers

0.21

 Newsp

0.18

 mast

0.17

 carriers

0.17

-Star

0.17

 carrier

0.17

 Herald

0.17

 Online

0.16

Activations Density 0.064%

mentions of news organizations and their publications

No Comments

No Known Activations