INDEX

Explanations

terms and concepts related to connections and interactions within a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ially

-0.18

lessly

-0.16

ly

-0.16

LY

-0.15

.datas

-0.14

ALLY

-0.14

äºİ

-0.14

uly

-0.13

uously

-0.13

isia

-0.13

POSITIVE LOGITS

ing

0.92

ING

0.54

ingen

0.34

ingt

0.33

ting

0.32

ning

0.31

ging

0.30

ë§ģ

0.29

ings

0.29

ãĥ³ãĤ°

0.27

Activations Density 0.825%

terms and concepts related to connections and interactions within a system

No Comments

No Known Activations