INDEX

Explanations

programming-related syntax and elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Glob

-0.17

oll

-0.15

 Guild

-0.15

_splits

-0.14

istrat

-0.14

oglob

-0.14

 folds

-0.14

 èĩªåĬ¨çĶŁæĪĲ

-0.14

 Friedman

-0.14

outer

-0.14

POSITIVE LOGITS

 drawing

0.26

 draw

0.25

draw

0.24

 stroke

0.24

 QPainter

0.23

 Draw

0.23

 DRAW

0.23

 Drawing

0.22

 draws

0.21

 drew

0.21

Activations Density 0.104%

programming-related syntax and elements

No Comments

No Known Activations