INDEX

Explanations

references to programming concepts and methods, particularly related to managing data or functions

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

Hur

-0.17

ysi

-0.17

rippling

-0.15

iciar

-0.15

Gal

-0.14

Lesson

-0.14

itness

-0.14

 Tato

-0.13

finalize

-0.13

ompiler

-0.13

POSITIVE LOGITS

 check

0.46

 checks

0.44

 checking

0.43

checks

0.37

check

0.36

 Checks

0.34

 Check

0.34

-check

0.34

_check

0.33

Check

0.32

Activations Density 0.269%

references to programming concepts and methods, particularly related to managing data or functions

No Comments

No Known Activations