INDEX

Explanations

the occurrence of the term "Mott" associated with places or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Cov

-0.15

ascus

-0.14

lazy

-0.14

 conclus

-0.14

enity

-0.14

nte

-0.14

undle

-0.14

wiÄĻ

-0.14

 Pension

-0.14

POSITIVE LOGITS

ucu

0.15

lu

0.15

è°·

0.15

uco

0.15

kÃ¡

0.15

chu

0.14

ael

0.14

quin

0.14

apon

0.14

 Donovan

0.14

Activations Density 0.005%

the occurrence of the term "Mott" associated with places or entities

No Comments

No Known Activations