INDEX

Explanations

references to shipping and mail-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

aina

-0.15

 cord

-0.15

 parking

-0.15

rost

-0.14

ray

-0.14

.setEditable

-0.14

Ð²Ð¾Ð±

-0.14

tera

-0.14

 Parking

-0.14

inity

-0.14

POSITIVE LOGITS

Fed

0.35

Fed

0.34

fed

0.29

fed

0.27

 cour

0.26

-fed

0.26

UPS

0.25

 FedEx

0.25

TNT

0.24

 parcel

0.24

Activations Density 0.018%

references to shipping and mail-related terms

No Comments

No Known Activations