INDEX

Explanations

technical terms and expressions related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ner

-0.15

unte

-0.15

Singleton

-0.14

ife

-0.14

ãģıãĤĵ

-0.14

ernel

-0.14

norm

-0.14

ikes

-0.14

 Hess

-0.14

edor

-0.14

POSITIVE LOGITS

 void

0.18

_typeof

0.17

:void

0.16

åŀĭ

0.16

ç±»åŀĭ

0.15

Ð¾Ð·Ñĸ

0.15

 datatype

0.15

 YYSTYPE

0.14

ÂłPS

0.14

ÏħÎ³

0.14

Activations Density 0.060%

technical terms and expressions related to programming and data structures

No Comments

No Known Activations