INDEX

Explanations

references to undergraduate education and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

åĢĻ

-0.16

rd

-0.15

/navigation

-0.15

lessness

-0.15

/datatables

-0.14

à¤¦

-0.14

ness

-0.14

sha

-0.14

RelativeTo

-0.14

_gradients

-0.14

POSITIVE LOGITS

-level

0.17

AFE

0.17

Ð¾ÑģÑĥÐ´

0.15

 lightly

0.15

hist

0.15

Ð¸ÑĦ

0.14

tah

0.14

_notifier

0.14

 Witt

0.14

auf

0.14

Activations Density 0.003%

references to undergraduate education and programs

No Comments

No Known Activations