INDEX

Explanations

references to images and visual media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

akes

-0.14

recision

-0.14

 (*((

-0.14

.gwt

-0.13

stagram

-0.13

owl

-0.13

å¯§

-0.13

 useClass

-0.13

imeo

-0.13

POSITIVE LOGITS

zer

0.15

Ã¢b

0.14

ailles

0.14

å½¦

0.14

artin

0.14

aras

0.14

PEC

0.14

inand

0.14

mlin

0.14

 slov

0.13

Activations Density 0.022%

references to images and visual media

No Comments

No Known Activations