INDEX

Explanations

words and phrases that convey emotional depth and complexity in personal or community contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

aka

-0.14

urat

-0.14

Ð¾Ð²Ð¾

-0.13

\Url

-0.13

à¥ĭà¤Ĥ,

-0.13

åıĬãģ³

-0.13

imli

-0.13

odel

-0.13

Thing

-0.12

 ÅŁi

-0.12

POSITIVE LOGITS

 alike

0.28

way

0.17

/etc

0.16

 manner

0.14

Ã³ng

0.14

-looking

0.14

-fe

0.14

 serta

0.14

 ÅŁekilde

0.13

 ways

0.13

Activations Density 0.088%

words and phrases that convey emotional depth and complexity in personal or community contexts

No Comments

No Known Activations