INDEX

Explanations

code and methods related to object properties and data structure manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Î¸Î¹

-0.18

conn

-0.15

yte

-0.15

ble

-0.14

 konkrÃ©t

-0.14

olut

-0.14

get

-0.14

.Domain

-0.14

POSITIVE LOGITS

 Doch

0.15

shal

0.15

\grid

0.15

fasta

0.15

reactstrap

0.15

ORA

0.15

issions

0.15

Ð¸ÑģÑĤÑĢÐ°

0.14

 Olson

0.14

ora

0.13

Activations Density 0.061%

code and methods related to object properties and data structure manipulations

No Comments

No Known Activations