INDEX

Explanations

names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 tamp

-0.16

Ð·Ñı

-0.15

ugin

-0.14

 ÏĩÏī

-0.14

 erfolgre

-0.14

 ê·¸ë¦¬ê³ł

-0.14

cpt

-0.14

BV

-0.13

ë¬¸ìĿĺ

-0.13

antz

-0.13

POSITIVE LOGITS

 said

0.43

said

0.27

 says

0.25

 ÑģÐºÐ°Ð·Ð°Ð»

0.23

say

0.22

è¯´

0.22

 saying

0.22

 Said

0.21

 added

0.21

 sagte

0.20

Activations Density 0.045%

names of people and places

No Comments

No Known Activations