INDEX

Explanations

references to different decades in the context of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ause

-0.14

à¥įà¤°à¤¸

-0.14

sb

-0.14

bert

-0.14

?action

-0.14

lest

-0.14

.resources

-0.13

æł·çļĦ

-0.13

gro

-0.13

.spi

-0.13

POSITIVE LOGITS

-long

0.20

-plus

0.19

-old

0.17

ä»¥ä¸Ĭ

0.15

ago

0.14

hound

0.14

Ø³Ùĥ

0.14

ilog

0.14

inte

0.14

wner

0.14

Activations Density 0.022%

references to different decades in the context of time

No Comments

No Known Activations