INDEX

Explanations

statistical comparisons and significant data points related to specific topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

airs

-0.17

 diseÃ±ador

-0.15

ellig

-0.14

 various

-0.14

Ã¡ÅĻe

-0.14

 twice

-0.13

ĻĤ

-0.13

lle

-0.13

lector

-0.13

th

-0.13

POSITIVE LOGITS

ernaut

0.18

tÃŃ

0.15

peria

0.15

 sets

0.15

Locale

0.15

erdale

0.14

irical

0.14

 Ø²Ø¯

0.14

embre

0.14

ÛĮØªÛĮ

0.14

Activations Density 0.507%

statistical comparisons and significant data points related to specific topics

No Comments

No Known Activations