INDEX

Explanations

references to valuable gifts or experiences that evoke emotion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ä°SÄ°

-0.12

Ð¾Ð½Ð°

-0.11

 tavs

-0.11

.nc

-0.11

 LPARAM

-0.10

Ð±Ð¾Ð¼

-0.10

 TypeInfo

-0.10

tesy

-0.10

opak

-0.10

ilk

-0.10

POSITIVE LOGITS

1.10

0.71

my

0.70

æĪĳ

0.64

 tÃ´i

0.63

 myself

0.62

 saya

0.56

ï¼ĮæĪĳ

0.56

Ive

0.49

æĪĳçļĦ

0.49

Activations Density 4.255%

references to valuable gifts or experiences that evoke emotion

No Comments

No Known Activations