INDEX

Explanations

phrases indicating conditionality or potentiality

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

 maybe

-0.16

appable

-0.16

amba

-0.15

atat

-0.15

 perhaps

-0.15

å°ĭ

-0.15

undy

-0.14

 possible

-0.14

\<^

-0.14

possible

-0.14

POSITIVE LOGITS

 well

0.36

well

0.34

 Might

0.33

might

0.31

 might

0.31

 Well

0.29

 WELL

0.27

Well

0.26

 wells

0.24

wel

0.23

Activations Density 0.038%

phrases indicating conditionality or potentiality

No Comments

No Known Activations