INDEX

Explanations

significant terms and markers related to academic and formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

è¡¡

-0.16

ä¹ī

-0.15

ayet

-0.14

Ú¯Ø§Ùĩ

-0.14

rike

-0.14

indr

-0.14

idar

-0.14

udge

-0.14

à¸Ļà¸ģ

-0.14

odule

-0.13

POSITIVE LOGITS

alers

0.15

achs

0.14

sters

0.14

AMS

0.14

 tapered

0.13

à¥Ĥà¤²

0.13

ASET

0.13

afort

0.13

alex

0.13

ÑĮ

0.13

Activations Density 0.070%

significant terms and markers related to academic and formal contexts

No Comments

No Known Activations