INDEX

Explanations

instances of object properties being assigned values or configurations

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

ipi

-0.15

 Podle

-0.15

ãģ®æĸ¹

-0.14

anders

-0.14

 provided

-0.14

 subject

-0.14

lage

-0.14

onces

-0.14

ontent

-0.13

uyá»ģn

-0.13

POSITIVE LOGITS

erea

0.18

ania

0.16

ÄĽk

0.14

recio

0.14

ķĮ

0.14

>>>(

0.14

terminal

0.14

æĢ

0.14

 sÃ©cur

0.13

æĸĹ

0.13

Activations Density 0.040%

instances of object properties being assigned values or configurations

No Comments

No Known Activations