INDEX

Explanations

references to software modules and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

fold

-0.23

ãģ¦

-0.18

ness

-0.17

leigh

-0.17

fall

-0.16

-0.15

fully

-0.15

iser

-0.15

burger

-0.15

most

-0.15

POSITIVE LOGITS

regunta

0.17

à¥Ģà¤¯

0.16

matic

0.16

hue

0.16

æĿĲ

0.15

elfast

0.15

.exports

0.15

okol

0.15

ummings

0.15

aments

0.14

Activations Density 0.049%

references to software modules and their functionalities

No Comments

No Known Activations