INDEX

Explanations

various categories and types related to media and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

rians

-0.14

ÅŁk

-0.13

ĶåĽŀ

-0.13

 Discount

-0.13

ey

-0.13

ute

-0.13

.getOwnProperty

-0.13

 filmer

-0.13

abet

-0.12

POSITIVE LOGITS

 Uncategorized

0.15

.localized

0.13

printStats

0.13

 tion

0.13

 --------------------

0.13

GINE

0.13

TEGER

0.13

igne

0.12

agnostics

0.12

ï¼Įå°ı

0.12

Activations Density 0.339%

various categories and types related to media and technology

No Comments

No Known Activations