INDEX

Explanations

references to the number four and its significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Antony

-0.15

 reopen

-0.14

all

-0.14

 three

-0.14

 Mine

-0.14

èĤ¥

-0.14

 ayak

-0.14

 pens

-0.14

spar

-0.14

 some

-0.14

POSITIVE LOGITS

argar

0.15

yre

0.15

endi

0.14

elik

0.14

iro

0.14

adÃŃ

0.14

ania

0.14

ÙĮ

0.14

zione

0.14

elin

0.14

Activations Density 0.062%

references to the number four and its significance

No Comments

No Known Activations