INDEX

Explanations

details related to fonts and typography

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

yer

-0.18

er

-0.17

GY

-0.16

à¸ļà¸²à¸¥

-0.15

 further

-0.15

-0.14

ches

-0.14

mime

-0.14

emento

-0.14

acs

-0.13

POSITIVE LOGITS

VRT

0.17

osate

0.16

LEAR

0.16

.googleapis

0.15

omu

0.15

IGHT

0.15

UME

0.15

 tetas

0.14

ensibly

0.14

rov

0.14

Activations Density 0.014%

details related to fonts and typography

No Comments

No Known Activations