INDEX

Explanations

references to terms and conditions related to service and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

erts

-0.19

gie

-0.16

anh

-0.16

ernen

-0.15

oday

-0.14

 blow

-0.14

ests

-0.14

oze

-0.14

erte

-0.14

tro

-0.14

POSITIVE LOGITS

Terms

0.22

 Terms

0.22

terms

0.21

/terms

0.20

 terms

0.19

 Conditions

0.18

 TERMS

0.18

Conditions

0.17

conditions

0.17

 conditions

0.16

Activations Density 0.009%

references to terms and conditions related to service and privacy policies

No Comments

No Known Activations