INDEX

Explanations

terms related to technical processes and systems operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

esteem

-0.16

orado

-0.16

-icons

-0.15

ÑĦÐ¾ÑĢÐ¼Ð¸

-0.15

strand

-0.15

Ã´me

-0.15

uetype

-0.15

atedRoute

-0.15

URRED

-0.15

chie

-0.14

POSITIVE LOGITS

 purposes

0.23

ability

0.22

via

0.21

by

0.21

ing

0.20

of

0.19

age

0.18

ance

0.18

0.17

ation

0.17

Activations Density 0.264%

terms related to technical processes and systems operations

No Comments

No Known Activations