INDEX

Explanations

references to language learning apps and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð¾Ð¼ÐµÑĤ

-0.14

ÐµÐ¹ÑģÑĤÐ²

-0.13

enze

-0.12

azen

-0.12

arend

-0.12

_robot

-0.12

arshal

-0.12

 ê²½ê¸°ëıĦ

-0.12

ynam

-0.11

 Ð²Ð½ÐµÑģ

-0.11

POSITIVE LOGITS

 language

0.56

 bilingual

0.54

 languages

0.54

 lingu

0.51

 linguistic

0.51

 Language

0.50

ilingual

0.48

 Languages

0.48

 Lingu

0.47

-language

0.47

Activations Density 0.426%

references to language learning apps and their functionalities

No Comments

No Known Activations