INDEX

Explanations

phrases that imply negation or a lack of something

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

graduate

-0.16

ovich

-0.16

(strtolower

-0.14

finity

-0.14

aoke

-0.14

asia

-0.13

ansom

-0.13

.edu

-0.13

ErrorHandler

-0.13

Äļ

-0.13

POSITIVE LOGITS

 longer

0.31

 Longer

0.24

 accident

0.23

 secret

0.23

 different

0.23

 Buen

0.23

 doubt

0.23

 wonder

0.23

 laughing

0.22

 mean

0.21

Activations Density 0.018%

phrases that imply negation or a lack of something

No Comments

No Known Activations