INDEX

Explanations

references to educational institutions and their achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

upert

-0.19

 universities

-0.18

 Universities

-0.17

 Harvard

-0.15

 vocational

-0.15

.edu

-0.15

EIF

-0.15

æ®¿

-0.15

ovu

-0.15

 tender

-0.14

POSITIVE LOGITS

 advising

0.23

 Under

0.22

 minors

0.22

 Advis

0.21

 advis

0.18

Under

0.18

NSF

0.18

 Prov

0.17

-under

0.17

Maj

0.17

Activations Density 0.192%

references to educational institutions and their achievements

No Comments

No Known Activations