INDEX

Explanations

keys and attributes related to data manipulation in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

å·

-0.17

BuilderFactory

-0.16

ignon

-0.14

dsl

-0.14

rowable

-0.14

uchen

-0.14

 Vernon

-0.14

LOAT

-0.14

uilder

-0.14

aven

-0.14

POSITIVE LOGITS

 value

0.54

 values

0.52

åĢ¼

0.49

value

0.46

åĢ¤

0.44

values

0.43

-value

0.42

 Values

0.41

-values

0.40

 ê°ĴìĿĦ

0.40

Activations Density 0.258%

keys and attributes related to data manipulation in programming

No Comments

No Known Activations