INDEX

Explanations

phrases related to scaling and extending capabilities or qualities of products and technologies

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

oten

-0.17

 MatSnackBar

-0.16

agal

-0.15

istrovstvÃŃ

-0.14

anzi

-0.14

amaz

-0.14

ekl

-0.14

 Prepared

-0.14

isay

-0.14

ereco

-0.13

POSITIVE LOGITS

onto

0.20

 onto

0.17

roe

0.16

 into

0.16

0.15

ãĤ¤ãĤ¯

0.15

åĪ°

0.14

ymax

0.14

Translated

0.14

Activations Density 0.129%

phrases related to scaling and extending capabilities or qualities of products and technologies

No Comments

No Known Activations