INDEX

Explanations

punctuation marks used to express emotions or pause in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 mine

-0.14

 coast

-0.14

dam

-0.13

ç¿¼

-0.13

 promot

-0.13

aqu

-0.13

emez

-0.13

ternal

-0.12

.tc

-0.12

 harbour

-0.12

POSITIVE LOGITS

 Roads

0.25

 Driving

0.22

 Views

0.21

 Heading

0.20

 Streets

0.20

 Downtown

0.20

 Traffic

0.20

 everywhere

0.19

 Weather

0.19

 Drive

0.19

Activations Density 0.108%

punctuation marks used to express emotions or pause in writing

No Comments

No Known Activations