INDEX

Explanations

references to comparisons or similarities between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

anik

-0.17

stan

-0.17

.Localization

-0.16

lsruhe

-0.14

unny

-0.14

ç«ĭãģ¦

-0.14

cts

-0.14

oras

-0.14

ãĥªãĥ¼ãĤº

-0.14

abi

-0.13

POSITIVE LOGITS

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.20

 napÅĻÃŃklad

0.19

ä¾ĭå¦Ĥ

0.18

ä¾ĭ

0.17

 ÙħØ«ÙĦØ§

0.17

 Ð½Ð°Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.15

 napÅĻ

0.15

 exemp

0.15

ÛĮØ±Ùĩ

0.15

 quelle

0.14

Activations Density 0.101%

references to comparisons or similarities between concepts or entities

No Comments

No Known Activations