INDEX

Explanations

references to periods of inactivity or breaks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ertz

-0.17

asp

-0.15

redicate

-0.15

osate

-0.15

 paginate

-0.14

PerPage

-0.14

ØªØ²

-0.14

åŃĹå¹ķ

-0.14

osg

-0.14

åĨħéĥ¨

-0.13

POSITIVE LOGITS

 period

0.31

 periods

0.30

period

0.22

 length

0.21

 lengths

0.21

 Period

0.20

 periodo

0.20

æľŁéĹ´

0.20

Period

0.19

 longer

0.19

Activations Density 0.140%

references to periods of inactivity or breaks

No Comments

No Known Activations