INDEX

Explanations

phrases related to conditions and requirements

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

ãģĻãģĻ

-0.17

ayan

-0.16

 Certain

-0.15

ichier

-0.15

 avoids

-0.15

 Avoid

-0.14

ãģ°ãģĭãĤĬ

-0.14

ugu

-0.14

vf

-0.14

 certain

-0.14

POSITIVE LOGITS

 usual

0.41

 normal

0.37

usual

0.35

 typical

0.32

 conventional

0.32

normal

0.32

 Ð¾Ð±ÑĭÑĩ

0.30

 traditional

0.30

 ordinary

0.29

 normally

0.29

Activations Density 0.007%

phrases related to conditions and requirements

No Comments

No Known Activations