INDEX

Explanations

references to guest bloggers and contributions on a blog

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

usch

-0.17

vs

-0.16

iro

-0.16

ldr

-0.16

osten

-0.15

.rs

-0.15

avit

-0.14

lr

-0.14

ril

-0.14

ÐµÐ²Ð¸Ñĩ

-0.13

POSITIVE LOGITS

ubu

0.17

acas

0.17

imuth

0.14

åĬ¡

0.14

Ãºp

0.14

BuilderFactory

0.14

_{}

0.14

onis

0.14

Ã¼zel

0.14

arity

0.13

Activations Density 0.013%

references to guest bloggers and contributions on a blog

No Comments

No Known Activations