INDEX

Explanations

instances of the syllable 'pe' in various contexts

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

moz

-0.16

iais

-0.15

ar

-0.15

oku

-0.15

se

-0.15

ogn

-0.14

ware

-0.14

sak

-0.14

ward

-0.13

 Boeh

-0.13

POSITIVE LOGITS

pe

0.26

Pe

0.25

Pe

0.24

oria

0.23

formance

0.22

acock

0.20

-pe

0.20

ptide

0.19

OPLE

0.19

FORMANCE

0.18

Activations Density 0.011%

instances of the syllable 'pe' in various contexts

No Comments

No Known Activations