INDEX

Explanations

elements related to a specific year or date

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Cities

-0.16

 city

-0.16

ÙĦÙĤ

-0.15

Ã¡Å¾

-0.15

-city

-0.15

 ThÃłnh

-0.15

 cities

-0.15

bjerg

-0.15

.chapter

-0.14

Î¼ÎŃ

-0.14

POSITIVE LOGITS

 village

0.26

 Village

0.26

æĿĳ

0.23

 villagers

0.21

 villages

0.19

illage

0.19

 Ø±ÙĪØ³ØªØ§

0.17

 Ð´ÐµÑĢÐµÐ²

0.16

 ÑģÐµÐ»Ð¾

0.16

 ÑģÐµÐ»Ð°

0.16

Activations Density 0.013%

elements related to a specific year or date

No Comments

No Known Activations

elements related to a specific year or date

No Comments

No Known Activations