INDEX

Explanations

programming-related terms and operations, specifically those dealing with data reading and type handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

è¶Ĭ

-0.16

ifacts

-0.15

Î¹Ïĩ

-0.14

combe

-0.14

ascade

-0.14

 Surface

-0.13

wig

-0.13

rientation

-0.13

arget

-0.13

pond

-0.13

POSITIVE LOGITS

 Mansion

0.16

ipeg

0.15

esser

0.14

-Version

0.14

Nev

0.14

Unicode

0.14

 Warehouse

0.14

(STD

0.14

kich

0.13

nex

0.13

Activations Density 0.030%

programming-related terms and operations, specifically those dealing with data reading and type handling

No Comments

No Known Activations