INDEX

Explanations

programming-related terms and structures, particularly those related to data paging and sorting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uitka

-0.20

rawer

-0.15

iales

-0.15

pector

-0.15

egin

-0.14

EIF

-0.14

ellan

-0.14

.chdir

-0.14

ereum

-0.14

legacy

-0.14

POSITIVE LOGITS

anta

0.18

otts

0.13

 algorithm

0.13

 Controls

0.13

 çħ

0.13

MPS

0.13

 serm

0.13

Wat

0.13

ngx

0.13

Activations Density 0.015%

programming-related terms and structures, particularly those related to data paging and sorting

No Comments

No Known Activations