INDEX

Explanations

terms and phrases related to agreements and consensus between parties

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

mayan

-0.16

aho

-0.16

uth

-0.15

nett

-0.15

Ø®Ø§ÙĨÙĩ

-0.15

uze

-0.15

ourg

-0.15

nage

-0.14

gang

-0.14

onto

-0.14

POSITIVE LOGITS

arian

0.24

 Reached

0.23

 reached

0.23

ually

0.23

ual

0.23

 between

0.21

 Between

0.20

EMENT

0.19

/dis

0.18

/ag

0.18

Activations Density 0.040%

terms and phrases related to agreements and consensus between parties

No Comments

No Known Activations