INDEX

Explanations

references to litigation and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ive

-0.18

lez

-0.16

hoot

-0.16

ing

-0.15

ean

-0.15

edException

-0.15

 Weather

-0.14

APA

-0.14

hall

-0.14

ees

-0.14

POSITIVE LOGITS

urgical

0.30

urgy

0.29

igation

0.28

igious

0.27

mus

0.25

igated

0.25

urg

0.23

igators

0.22

igate

0.22

igator

0.21

Activations Density 0.013%

references to litigation and legal terminology

No Comments

No Known Activations