INDEX

Explanations

references to specific individuals and their notable characteristics or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.25

ing

-0.22

esi

-0.21

ee

-0.21

-0.19

-0.18

es

-0.18

yh

-0.18

ean

-0.17

Ð¾Ð¾Ð±ÑĢÐ°Ð·

-0.17

POSITIVE LOGITS

ding

0.33

yssey

0.32

dy

0.28

ders

0.27

ded

0.26

den

0.24

der

0.23

ds

0.22

nocenÃŃ

0.21

di

0.21

Activations Density 0.027%

references to specific individuals and their notable characteristics or activities

No Comments

No Known Activations