INDEX

Explanations

sections related to placeholder or dummy content for individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ãĤ¿ãĥ«

-0.14

->↵

-0.14

UBE

-0.14

 automÃ¡t

-0.14

rer

-0.13

ending

-0.13

having

-0.13

 Ð²Ð½Ð¸Ð¼

-0.13

prox

-0.13

otta

-0.13

POSITIVE LOGITS

 currently

0.37

 presently

0.29

 Currently

0.29

currently

0.28

Currently

0.28

 listed

0.24

 Listings

0.22

 listings

0.20

 CURRENT

0.20

 current

0.20

Activations Density 0.004%

sections related to placeholder or dummy content for individuals

No Comments

No Known Activations