INDEX

Explanations

references to academic programs and interdisciplinary studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Suc

-0.15

rade

-0.14

 Phen

-0.14

afort

-0.14

íį¼

-0.13

æĮ¥

-0.13

jug

-0.13

oogle

-0.13

muz

-0.13

alls

-0.13

POSITIVE LOGITS

 majors

0.30

 minors

0.28

 Major

0.28

Maj

0.27

 major

0.27

 concentration

0.25

ect

0.24

 courses

0.23

 Minor

0.23

 minor

0.23

Activations Density 0.127%

references to academic programs and interdisciplinary studies

No Comments

No Known Activations