INDEX

Explanations

snippets related to code and structure in programming languages, especially focusing on errors and data definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

znik

-0.15

aggi

-0.15

aries

-0.15

llen

-0.15

erver

-0.14

.getLength

-0.14

ngle

-0.14

ques

-0.14

 ê¸ī

-0.14

POSITIVE LOGITS

auf

0.15

sphere

0.14

jni

0.14

sad

0.14

izzle

0.14

æĭ¥

0.13

 faker

0.13

andan

0.13

è·Ŀ

0.13

 Wich

0.13

Activations Density 0.041%

snippets related to code and structure in programming languages, especially focusing on errors and data definitions

No Comments

No Known Activations