INDEX

Explanations

references to agreements or deals 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 garn

-0.15

ÑĤÐ°Ð¶

-0.14

rq

-0.14

createClass

-0.14

ARDS

-0.14

ream

-0.14

sab

-0.14

cobra

-0.14

alat

-0.13

 barric

-0.13

POSITIVE LOGITS

 agreement

0.30

 agreements

0.26

 Agreement

0.25

 deal

0.22

 arrangement

0.21

 deals

0.20

 signed

0.20

 agreeing

0.20

 agree

0.20

ag

0.20

Activations Density 0.311%

references to agreements or deals between parties

No Comments

No Known Activations

references to agreements or deals between parties

No Comments

No Known Activations