INDEX

Explanations

references to legal terms and contexts associated with jurisdictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 ç±³

-0.15

setChecked

-0.15

/cache

-0.14

Ðĭ

-0.14

CharacterSet

-0.14

hci

-0.14

.TabStop

-0.13

Ð½Ð°ÑĢ

-0.13

ãĥ©ãĤ¹

-0.13

Enlarge

-0.13

POSITIVE LOGITS

Ch

1.55

ch

1.30

Ch

1.22

_ch

0.94

.ch

0.81

ch

0.80

.Ch

0.79

-Ch

0.79

-ch

0.76

(ch

0.76

Activations Density 0.649%

references to legal terms and contexts associated with jurisdictions

No Comments

No Known Activations