INDEX

Explanations

terminologies related to social welfare and health services

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

 Dort

-0.16

ongo

-0.15

Ved

-0.15

PKG

-0.15

emu

-0.14

ocked

-0.14

Ya

-0.13

vek

-0.13

inki

-0.13

ãĥ¼ãĥĨ

-0.13

POSITIVE LOGITS

 Philippine

0.30

Php

0.28

 Manila

0.28

Php

0.27

 Filip

0.27

 Filipino

0.26

mga

0.25

 advoc

0.25

 barang

0.24

 Duterte

0.24

Activations Density 0.583%

terminologies related to social welfare and health services

No Comments

No Known Activations