INDEX

Explanations

symbols and phrases related to specific time periods, particularly emphasizing various years and first seasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

(æľĪ

-0.15

 Spoj

-0.15

Mil

-0.15

ingleton

-0.15

unate

-0.15

 figure

-0.14

alar

-0.14

Mil

-0.13

çµ¡

-0.13

ÐµÐ·Ð¿ÐµÑĩ

-0.13

POSITIVE LOGITS

olley

0.17

Ãºsqueda

0.15

 trá»Ŀi

0.15

 atenciÃ³n

0.15

vÄĽ

0.14

 Kremlin

0.14

oldt

0.13

ead

0.13

Ã«l

0.13

ãĤ¦ãĥ³

0.13

Activations Density 0.036%

symbols and phrases related to specific time periods, particularly emphasizing various years and first seasons

No Comments

No Known Activations