INDEX

Explanations

references to various brands and products in context

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

atica

-0.15

Pra

-0.14

icro

-0.14

uala

-0.14

 Stam

-0.14

ä¸²

-0.14

agal

-0.13

 pres

-0.13

 Wilson

-0.13

Wilson

-0.13

POSITIVE LOGITS

etik

0.17

ddb

0.17

 /*!<

0.16

ì¸

0.16

à¸¶

0.14

ITES

0.14

Fcn

0.14

"":

0.14

nip

0.14

OLID

0.14

Activations Density 0.107%

references to various brands and products in context

No Comments

No Known Activations