INDEX

Explanations

items, products, and their associated details or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

/colors

-0.16

ãĥ³ãĥĨãĤ£

-0.15

utenberg

-0.14

ãĤ¿ãĤ¤

-0.14

ordion

-0.14

×ķ

-0.14

bruary

-0.14

ayscale

-0.14

@email

-0.14

enuity

-0.14

POSITIVE LOGITS

 ==========

0.14

 ÃĿ

0.14

bach

0.14

zu

0.14

osate

0.14

nio

0.14

zim

0.13

ghi

0.13

asu

0.13

 awakeFromNib

0.13

Activations Density 0.239%

items, products, and their associated details or classifications

No Comments

No Known Activations