INDEX

Explanations

numerical data related to indigenous populations and their counterparts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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£¨

-0.16

aments

-0.15

 LGPL

-0.15

Ì§

-0.14

iqueta

-0.14

gross

-0.14

 táº·ng

-0.14

çĢ¬

-0.14

 STDCALL

-0.14

Han

-0.14

POSITIVE LOGITS

 admission

0.27

 Admission

0.24

 screening

0.23

 Direct

0.23

 Screening

0.21

 admissions

0.21

 direct

0.20

 screenings

0.20

.screen

0.20

screen

0.20

Activations Density 0.006%

numerical data related to indigenous populations and their counterparts

No Comments

No Known Activations