INDEX

Explanations

specific numerical and technical identifiers related to data sets and measurements

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

chester

-0.15

enery

-0.15

ickness

-0.14

acity

-0.14

cÃŃ

-0.14

insic

-0.14

ä»ĬæĹ¥

-0.14

ÙĦØ§ÙĤ

-0.13

amet

-0.13

herence

-0.13

POSITIVE LOGITS

Kh

0.25

Kh

0.21

 Pentagon

0.21

 Roths

0.21

 Zionist

0.18

 pent

0.18

 Sabb

0.17

kh

0.17

cab

0.17

 Bilder

0.16

Activations Density 0.000%

specific numerical and technical identifiers related to data sets and measurements

No Comments

No Known Activations