INDEX

Explanations

programming or coding-related terms and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Ben

-0.14

Bay

-0.13

OMPI

-0.13

 Pompe

-0.13

.WebControls

-0.13

DSL

-0.13

ikt

-0.13

sit

-0.13

usa

-0.13

 Vernon

-0.13

POSITIVE LOGITS

Gatt

0.29

Characteristic

0.29

 characteristic

0.29

.UUID

0.27

BLE

0.26

Uuid

0.25

 UUID

0.25

UUID

0.25

ble

0.24

.uuid

0.24

Activations Density 0.030%

programming or coding-related terms and syntax

No Comments

No Known Activations