INDEX

Explanations

words and phrases that express dependency or connection between ideas and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Î»Ïħ

-0.17

ilter

-0.16

Fat

-0.16

BufferData

-0.15

æ·

-0.15

eyn

-0.15

?page

-0.15

åĦ

-0.14

ogra

-0.14

POSITIVE LOGITS

 zwar

0.15

/or

0.14

Ð±Ð¾

0.14

 practise

0.14

åŃĺäºİ

0.13

 ÑĤÐ¸

0.13

ire

0.13

udy

0.13

.jp

0.13

 Unter

0.13

Activations Density 0.253%

words and phrases that express dependency or connection between ideas and actions

No Comments

No Known Activations