INDEX

Explanations

references to programming language features and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

uld

-0.16

èĳī

-0.16

=-=-=-=-

-0.16

=-=-

-0.16

STL

-0.15

kiego

-0.15

xad

-0.14

 stol

-0.14

irst

-0.14

ctors

-0.14

POSITIVE LOGITS

0.35

mente

0.27

iss

0.24

emente

0.22

ISS

0.22

izzato

0.21

ibus

0.19

isi

0.19

istica

0.19

ucci

0.19

Activations Density 0.012%

references to programming language features and their functionalities

No Comments

No Known Activations