INDEX

Explanations

words and phrases related to examples and comparisons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

yon

-0.16

ovenant

-0.15

OLA

-0.15

aklÄ±

-0.15

agar

-0.15

iese

-0.14

ulong

-0.14

ola

-0.14

åıĪ

-0.14

 Sierra

-0.14

POSITIVE LOGITS

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.27

 example

0.25

 ÙħØ«ÙĦØ§

0.25

 napÅĻÃŃklad

0.24

example

0.22

 ÐĿÐ°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.22

ä¾ĭå¦Ĥ

0.21

 Ð½Ð°Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.19

ä¾ĭ

0.19

_example

0.18

Activations Density 0.398%

words and phrases related to examples and comparisons in various contexts

No Comments

No Known Activations