INDEX

Explanations

references to entities and phenomena involving unknowns and measurements in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 gender

-0.15

obus

-0.14

 aliens

-0.14

 person

-0.14

 Heap

-0.13

 alien

-0.13

sex

-0.13

ovah

-0.13

İ·

-0.13

istrovstvÃŃ

-0.13

POSITIVE LOGITS

 mote

0.17

]={↵

0.16

tow

0.16

UBE

0.15

æĶ¹éĿ©

0.15

terior

0.14

arkan

0.14

Î³ÏĮ

0.14

ableObject

0.14

ainter

0.14

Activations Density 0.030%

references to entities and phenomena involving unknowns and measurements in a scientific context

No Comments

No Known Activations