INDEX

Explanations

references to educational materials and resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.TextAlignment

-0.15

StackNavigator

-0.15

celik

-0.15

ign

-0.15

/trunk

-0.15

ãĥ¼ãĥ³

-0.14

adar

-0.14

nda

-0.14

/pm

-0.14

Uploaded

-0.14

POSITIVE LOGITS

 companion

0.23

 accompanying

0.21

 accompany

0.19

 accompanies

0.18

 acompan

0.18

 Companion

0.18

 bonus

0.18

 accom

0.17

 ÐĴÐ¸

0.16

 kÃ¨m

0.15

Activations Density 0.087%

references to educational materials and resources

No Comments

No Known Activations

references to educational materials and resources

No Comments

No Known Activations