INDEX

Explanations

references to illustrations and visual art

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alic

-0.18

est

-0.17

ÑģÑĭÐ»

-0.17

ish

-0.17

VISION

-0.16

Ð²ÑģÑı

-0.16

essa

-0.16

Ð²ÑĸÐ»ÑĮ

-0.16

ORM

-0.15

rous

-0.15

POSITIVE LOGITS

oir

0.16

mente

0.15

ERCHANT

0.15

ÏģÎ¹Î¿

0.15

chema

0.14

dum

0.14

mith

0.14

mek

0.14

lcd

0.13

Eig

0.13

Activations Density 0.022%

references to illustrations and visual art

No Comments

No Known Activations