INDEX

Explanations

keywords and names related to technological and organizational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

soever

-0.17

alent

-0.15

«ĺ

-0.14

ivia

-0.14

olume

-0.14

 INTERRUPTION

-0.14

esium

-0.14

æĻĵ

-0.13

 ÑĢÐµÑĩ

-0.13

oyal

-0.13

POSITIVE LOGITS

tru

0.17

scoped

0.15

Haw

0.14

rawl

0.14

uhl

0.14

 serialVersionUID

0.14

inker

0.13

atron

0.13

tb

0.13

inx

0.13

Activations Density 0.422%

keywords and names related to technological and organizational contexts

No Comments

No Known Activations