INDEX

Explanations

references to significant events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

iza

-0.15

campo

-0.15

Campo

-0.15

 Vinci

-0.14

opher

-0.13

±

-0.13

icular

-0.13

incer

-0.13

ampo

-0.13

uzzer

-0.13

POSITIVE LOGITS

autoplay

0.19

 Stocks

0.17

 Sense

0.17

Magnitude

0.17

 Markets

0.16

 stock

0.16

 Prince

0.16

US

0.16

 Donald

0.16

IOC

0.15

Activations Density 0.276%

references to significant events or conditions

No Comments

No Known Activations