INDEX

Explanations

concepts related to evaluation and improvement processes

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

 various

-0.17

ç«ĭãģ¦

-0.15

 versions

-0.14

mga

-0.14

 types

-0.14

 individuals

-0.14

sects

-0.14

 ones

-0.14

äºĽ

-0.14

ungle

-0.14

POSITIVE LOGITS

 item

0.35

 piece

0.30

 element

0.22

ä¹ĭä¸Ģ

0.22

 Piece

0.22

item

0.21

piece

0.21

 molecule

0.20

 ITEM

0.20

 Item

0.20

Activations Density 1.093%

concepts related to evaluation and improvement processes

No Comments

No Known Activations