INDEX

Explanations

programming-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 tslint

-0.19

 eslint

-0.15

imony

-0.15

eration

-0.15

ani

-0.15

Saga

-0.14

Å¾el

-0.14

mag

-0.14

ferences

-0.14

 SqlDbType

-0.13

POSITIVE LOGITS

gro

0.40

gro

0.39

Gro

0.36

Gro

0.35

 Closure

0.30

 closure

0.29

_closure

0.29

Closure

0.28

 closures

0.25

 groove

0.24

Activations Density 0.007%

programming-related terms and concepts

No Comments

No Known Activations