INDEX

Explanations

references to integration in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

azzo

-0.16

NING

-0.15

Liked

-0.15

chod

-0.14

ê¹

-0.14

egas

-0.14

.joda

-0.14

ëľ

-0.14

 demokrat

-0.14

wed

-0.14

POSITIVE LOGITS

/embed

0.26

 into

0.22

 seamlessly

0.19

 within

0.19

 circuits

0.17

aps

0.17

 sexes

0.17

Ð´ÐµÐ¹ÑģÑĤÐ²

0.16

within

0.16

 elements

0.16

Activations Density 0.049%

references to integration in various contexts

No Comments

No Known Activations