INDEX

Explanations

references to specific dates and geographical or jurisdictional terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

PropertyDescriptor

-0.15

urovision

-0.15

iaux

-0.15

oux

-0.15

 Clown

-0.14

folio

-0.14

ades

-0.14

iffe

-0.14

 Bald

-0.14

ķĮ

-0.14

POSITIVE LOGITS

eller

0.17

nde

0.16

ugar

0.16

huy

0.15

usher

0.15

Tro

0.14

.ActionListener

0.14

hci

0.14

 Joel

0.14

strup

0.14

Activations Density 0.288%

references to specific dates and geographical or jurisdictional terms

No Comments

No Known Activations