INDEX

Explanations

proper nouns and names associated with people, places, and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

NIL

-0.15

quam

-0.14

isha

-0.14

oje

-0.14

jet

-0.14

Ð°Ð´Ñĥ

-0.14

cepts

-0.14

Sab

-0.14

 keypad

-0.14

Jet

-0.13

POSITIVE LOGITS

 coats

0.15

 Ð´ÐµÐ½

0.15

 CreateMap

0.15

 SetProperty

0.15

oreach

0.14

Î¼Î¼Î±

0.14

"crypto

0.14

olor

0.14

 DÃ¼n

0.14

neider

0.13

Activations Density 0.081%

proper nouns and names associated with people, places, and entities

No Comments

No Known Activations