INDEX

Explanations

quantifiers describing the frequency or prevalence of situations, specifically "some" and "many."

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

eree

-0.15

alue

-0.14

ÑŁ

-0.14

ãģŁãģĹ

-0.14

æĶ¿

-0.14

 automÃ¡t

-0.14

asmus

-0.14

irs

-0.13

 :↵↵↵↵

-0.13

Hat

-0.13

POSITIVE LOGITS

ÏĢÎ¯

0.17

unden

0.15

adla

0.14

gev

0.14

cence

0.14

æĥħåĨµ

0.14

CED

0.13

.spi

0.13

iot

0.13

osis

0.13

Activations Density 0.091%

quantifiers describing the frequency or prevalence of situations, specifically "some" and "many."

No Comments

No Known Activations