INDEX

Explanations

terms related to taxes and taxation

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

.lng

-0.15

åĲĪ

-0.15

ba

-0.15

sil

-0.15

uppe

-0.14

enf

-0.14

ENG

-0.14

rav

-0.14

ì¼ĵ

-0.14

aque

-0.14

POSITIVE LOGITS

 Vinci

0.16

RootElement

0.15

erseniz

0.15

 Crimson

0.15

ayan

0.15

igit

0.14

errat

0.14

kker

0.14

iÅ¾

0.14

Ð¸Ð¼Ð²

0.14

Activations Density 0.018%

terms related to taxes and taxation

No Comments

No Known Activations