INDEX

Explanations

elements and attributes in project configuration files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 rugged

-0.14

 meiden

-0.14

ander

-0.14

 Ø§ÙĦÙĨØ³

-0.14

izi

-0.14

blade

-0.14

ulp

-0.14

ollen

-0.14

chin

-0.14

ersh

-0.14

POSITIVE LOGITS

aji

0.15

º

0.15

quer

0.14

ãģĭãģĳ

0.13

Skeleton

0.13

tab

0.13

tpl

0.13

SEC

0.13

Activations Density 0.011%

elements and attributes in project configuration files

No Comments

No Known Activations