INDEX

Explanations

instances of the word "use" and related coding constructs or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ourke

-0.14

ishi

-0.14

/umd

-0.14

untas

-0.14

acs

-0.14

åŀ

-0.14

 hood

-0.14

 pylint

-0.14

stery

-0.13

hti

-0.13

POSITIVE LOGITS

 crate

0.33

 rust

0.32

 Rust

0.32

rust

0.31

.rs

0.30

 Cargo

0.28

 cargo

0.26

 crates

0.26

 trait

0.25

Cargo

0.24

Activations Density 0.004%

instances of the word "use" and related coding constructs or functions

No Comments

No Known Activations