INDEX

Explanations

references to measurement and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ulet

-0.14

ullet

-0.14

ï»¿#

-0.14

zej

-0.14

chai

-0.14

 kolo

-0.14

vez

-0.13

oy

-0.13

ault

-0.13

rit

-0.13

POSITIVE LOGITS

igar

0.19

ibu

0.15

 picture

0.15

ampo

0.14

igated

0.14

erro

0.14

anas

0.14

gment

0.14

asa

0.14

amet

0.14

Activations Density 0.055%

references to measurement and quantities

No Comments

No Known Activations