INDEX

Explanations

phrases and terms related to new product launches or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Burgess

-0.15

Recent

-0.15

htub

-0.15

Ø¢Ø®Ø±

-0.14

 Recent

-0.14

ãĥ³ãĥģ

-0.14

 ná»ķi

-0.14

 recent

-0.14

Ã¦r

-0.13

tk

-0.13

POSITIVE LOGITS

new

0.23

æĸ°çļĦ

0.23

new

0.20

 Ð½Ð¾Ð²Ð¾Ð³Ð¾

0.18

(new

0.17

new

0.17

 anew

0.16

 neuen

0.16

 nuevas

0.16

 nouveaux

0.15

Activations Density 0.078%

phrases and terms related to new product launches or initiatives

No Comments

No Known Activations