INDEX

Explanations

legal terms and concepts related to employment law and discrimination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

endl

-0.16

Äįan

-0.15

acer

-0.15

ActionButton

-0.15

istrat

-0.15

Å¾ÃŃ

-0.14

 regularization

-0.14

 Laws

-0.14

adel

-0.14

iasi

-0.14

POSITIVE LOGITS

 tests

0.33

 test

0.31

tests

0.28

test

0.25

 Tests

0.25

 ÑĤÐµÑģÑĤ

0.24

-tests

0.23

Tests

0.23

 analysis

0.22

 Test

0.21

Activations Density 0.139%

legal terms and concepts related to employment law and discrimination

No Comments

No Known Activations