INDEX

Explanations

references to geographic locations and urban areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Atlas

-0.19

@$_

-0.16

edom

-0.15

æĵį

-0.15

loub

-0.15

imoto

-0.15

à¸Ļà¸§

-0.14

idak

-0.14

marvin

-0.14

embro

-0.14

POSITIVE LOGITS

ums

0.15

å»·

0.15

é³´

0.14

osis

0.14

setItem

0.14

avanaugh

0.14

uye

0.14

/n

0.14

 rozh

0.14

ayi

0.14

Activations Density 0.008%

references to geographic locations and urban areas

No Comments

No Known Activations