INDEX

Explanations

names and titles of individuals or entities, particularly those in leadership or noteworthy roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

InSection

-0.12

ToObject

-0.12

()?.

-0.12

ombres

-0.12

awei

-0.12

 Ø®ÙĦÙģ

-0.12

 Ø±ÙĤÙħ

-0.12

&&!

-0.12

ãħłãħł

-0.12

ODULE

-0.11

POSITIVE LOGITS

 Founder

0.25

of

0.25

aka

0.25

Founder

0.25

 founder

0.24

 owner

0.24

/www

0.22

Owner

0.22

www

0.21

 Owner

0.21

Activations Density 0.226%

names and titles of individuals or entities, particularly those in leadership or noteworthy roles

No Comments

No Known Activations