INDEX

Explanations

instances of the word "use" and related structural elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ãĥ¼ãĤ¹

-0.16

anus

-0.16

stery

-0.16

ourke

-0.15

åŀ

-0.15

orsch

-0.15

 unheard

-0.14

.amazonaws

-0.14

/cards

-0.14

ActionCreators

-0.14

POSITIVE LOGITS

 crate

0.32

 crates

0.21

 Crate

0.20

 serde

0.20

crate

0.20

std

0.19

std

0.19

.rs

0.18

 Cargo

0.18

 Diesel

0.17

Activations Density 0.001%

instances of the word "use" and related structural elements in code

No Comments

No Known Activations