INDEX

Explanations

blocks or pairs of braces in various programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 CGRectGet

-0.18

ë¡

-0.15

lings

-0.15

eland

-0.15

iale

-0.14

declspec

-0.14

asca

-0.14

lest

-0.14

#End

-0.14

est

-0.14

POSITIVE LOGITS

uzey

0.17

 Morm

0.15

.openConnection

0.15

eldo

0.15

æ·»

0.15

ãĥ³ãĥĸ

0.14

arem

0.14

rica

0.14

.Extension

0.14

 NotImplemented

0.14

Activations Density 0.065%

blocks or pairs of braces in various programming contexts

No Comments

No Known Activations