INDEX

Explanations

terms related to wages and salaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

toi

-0.15

Ã²ng

-0.15

iae

-0.15

imation

-0.15

unday

-0.15

ÑĤÐ¸Ð½

-0.14

gency

-0.14

anmar

-0.14

clusion

-0.13

 Expanded

-0.13

POSITIVE LOGITS

 structures

0.27

 structure

0.27

 scales

0.26

 Structures

0.24

 Structure

0.23

Structure

0.23

 earners

0.21

 levels

0.21

 STRUCT

0.20

 freeze

0.20

Activations Density 0.040%

terms related to wages and salaries

No Comments

No Known Activations