INDEX

Explanations

terms related to relative comparisons in various contexts

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

uality

-0.18

æĸĻ

-0.17

nat

-0.17

ancial

-0.15

aper

-0.15

unge

-0.14

StackNavigator

-0.14

ÙħÙĦ

-0.14

esis

-0.14

nos

-0.14

POSITIVE LOGITS

 humidity

0.23

(relative

0.21

 relative

0.20

 newcomer

0.19

 olarak

0.19

-relative

0.18

 Relative

0.18

Hum

0.18

humidity

0.18

 merits

0.17

Activations Density 0.023%

terms related to relative comparisons in various contexts

No Comments

No Known Activations