INDEX

Explanations

collections and data structure-related terms in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ervo

-0.16

ampo

-0.15

orest

-0.15

Shr

-0.14

ppo

-0.14

fono

-0.14

omu

-0.14

fav

-0.13

eba

-0.13

MEA

-0.13

POSITIVE LOGITS

oodle

0.16

inae

0.15

-fontawesome

0.14

umbo

0.14

ÑģÑĤÐµ

0.14

 Pall

0.14

Ð»Ð¸Ð½Ð¸

0.13

 Verse

0.13

ardy

0.13

eliac

0.13

Activations Density 0.008%

collections and data structure-related terms in programming

No Comments

No Known Activations