INDEX

Explanations

XML-like tags or markup formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

swers

-0.16

qui

-0.15

cobra

-0.15

hev

-0.15

 Ð·Ð°ÐºÐ»Ð°Ð´

-0.15

pipeline

-0.14

ABCDEFGHIJKLMNOP

-0.14

notated

-0.14

VAS

-0.14

hee

-0.14

POSITIVE LOGITS

arth

0.15

deki

0.15

uns

0.15

alaria

0.15

enas

0.14

jezd

0.14

umbnails

0.14

UnitOfWork

0.14

erm

0.14

pel

0.14

Activations Density 0.003%

XML-like tags or markup formats

No Comments

No Known Activations