INDEX

Explanations

words related to entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

afone

-0.17

enate

-0.15

affles

-0.15

 Speedway

-0.15

ucha

-0.15

gorm

-0.15

alar

-0.15

raith

-0.15

 Warfare

-0.15

ofilm

-0.15

POSITIVE LOGITS

anny

0.17

à¹ģà¸¥

0.15

ook

0.15

raquo

0.15

Kes

0.15

 kvin

0.14

 SOLD

0.14

ief

0.14

inÃ§

0.14

oment

0.13

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations