INDEX

Explanations

terms and phrases related to procedures and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 themselves

-0.17

.scalablytyped

-0.16

WithMany

-0.15

¼åĲĪ

-0.15

asal

-0.15

laus

-0.14

argest

-0.14

Ú¯ÙĪÛĮ

-0.14

_hdl

-0.14

 aren

-0.14

POSITIVE LOGITS

 exists

0.46

 existed

0.35

 exist

0.35

exists

0.33

 existe

0.29

 Exist

0.29

 accompanies

0.29

 Exists

0.29

exist

0.27

was

0.26

Activations Density 0.456%

terms and phrases related to procedures and regulations

No Comments

No Known Activations