INDEX

Explanations

references to specific organizations and their relationships to industries or sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

acular

-0.17

ushima

-0.15

.getOwnProperty

-0.15

 BaseService

-0.15

 Mist

-0.14

 Kraj

-0.14

èİī

-0.14

decimal

-0.14

istan

-0.14

POSITIVE LOGITS

aeda

0.18

edia

0.15

¤íĶĦ

0.15

ÙĪØªØ±

0.15

antino

0.15

Ð¾ÑģÑĢÐµÐ´

0.14

Ú¯Ø±Ø§ÙĨ

0.14

inz

0.14

rlen

0.13

_lite

0.13

Activations Density 0.390%

references to specific organizations and their relationships to industries or sectors

No Comments

No Known Activations