INDEX

Explanations

programming concepts related to types and type systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 CActive

-0.14

egan

-0.14

 GUIStyle

-0.14

 UIResponder

-0.14

ÎºÏĮ

-0.14

orer

-0.14

tering

-0.13

 îł

-0.13

Ñ

-0.13

ietf

-0.13

POSITIVE LOGITS

 type

0.25

 typing

0.23

 generics

0.22

 covariance

0.22

 casting

0.22

type

0.21

 æ³

0.21

.type

0.21

åŀĭ

0.21

 generic

0.21

Activations Density 0.052%

programming concepts related to types and type systems

No Comments

No Known Activations