INDEX

Explanations

terms and structures related to programming concepts and animations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oje

-0.15

emer

-0.14

ÑĢÐµÑħ

-0.14

 freopen

-0.14

prov

-0.14

âĻĢ

-0.14

aterno

-0.13

 Scalars

-0.13

GenerationStrategy

-0.13

AndView

-0.13

POSITIVE LOGITS

 animation

0.51

 anim

0.50

 Animation

0.45

 animations

0.44

 Anim

0.44

 animated

0.41

 animate

0.40

Animation

0.37

anim

0.37

 animator

0.37

Activations Density 0.300%

terms and structures related to programming concepts and animations in code

No Comments

No Known Activations