INDEX

Explanations

references to academic and professional achievements/honors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

_neurons

-0.18

aroo

-0.15

avanaugh

-0.15

eref

-0.15

è³ŀ

-0.15

askell

-0.14

swagger

-0.14

å±Ĩ

-0.14

washer

-0.14

 Wend

-0.13

POSITIVE LOGITS

 receive

0.22

 RECEIVE

0.22

 recently

0.21

 rece

0.20

 Receive

0.20

 Rece

0.20

 receives

0.20

 RECE

0.20

 receiving

0.20

 zosta

0.20

Activations Density 0.059%

references to academic and professional achievements/honors

No Comments

No Known Activations