INDEX

Explanations

advice and tips related to personal development and self-care

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ison

-0.16

 Excell

-0.15

ully

-0.15

adil

-0.14

ISON

-0.14

ä½ľ

-0.14

ULL

-0.14

yun

-0.14

ullo

-0.14

frauen

-0.14

POSITIVE LOGITS

 Burl

0.15

èķī

0.14

lic

0.14

latin

0.13

duc

0.13

dere

0.13

Ð¸ÐºÑĥ

0.13

 Stem

0.13

alic

0.13

Activations Density 0.509%

advice and tips related to personal development and self-care

No Comments

No Known Activations