INDEX

Explanations

references to "smart" technology and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

bsite

-0.17

anager

-0.16

ors

-0.16

anine

-0.15

afa

-0.15

ftware

-0.15

athan

-0.15

ataire

-0.15

inous

-0.15

ureka

-0.15

POSITIVE LOGITS

yp

0.21

ened

0.21

ly

0.21

ness

0.19

phones

0.19

ale

0.19

PHONE

0.19

est

0.19

visor

0.19

ening

0.18

Activations Density 0.016%

references to "smart" technology and related concepts

No Comments

No Known Activations