INDEX

Explanations

phrases that imply addition or reference to additional elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

)application

-0.16

laden

-0.15

izard

-0.15

ÑģÐ»Ð¸

-0.15

ounge

-0.15

surf

-0.14

 Wich

-0.14

Î³Î³ÎµÎ»

-0.14

ury

-0.14

ORIZED

-0.13

POSITIVE LOGITS

chemas

0.17

roll

0.17

igin

0.16

IDS

0.15

Gow

0.14

 GUIDE

0.14

ceph

0.14

oday

0.14

IMIT

0.13

igen

0.13

Activations Density 0.012%

phrases that imply addition or reference to additional elements

No Comments

No Known Activations