INDEX

Explanations

references to internet memes and popular culture

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

rum

-0.18

cente

-0.15

Cliente

-0.14

client

-0.14

_cliente

-0.14

 Elem

-0.14

Î³Î¿Ïħ

-0.14

atsby

-0.13

 Client

-0.13

eel

-0.13

POSITIVE LOGITS

iaux

0.16

omon

0.15

uell

0.15

ìŀħ

0.15

ãĤĢ

0.14

ification

0.14

 friendly

0.14

 corner

0.14

corner

0.14

ery

0.14

Activations Density 0.115%

references to internet memes and popular culture

No Comments

No Known Activations