INDEX

Explanations

punctuation and expressions related to questioning or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Flex

-0.17

 Flex

-0.16

ondo

-0.15

andex

-0.15

ãĥĶãĥ¼

-0.15

ubat

-0.15

ovit

-0.15

 Polymer

-0.14

Ukr

-0.14

flex

-0.14

POSITIVE LOGITS

 Lost

0.36

Lost

0.31

 Desmond

0.29

 Locke

0.28

 Island

0.28

 island

0.27

 Ocean

0.27

 Sawyer

0.25

Hur

0.25

 lost

0.23

Activations Density 0.004%

punctuation and expressions related to questioning or uncertainty

No Comments

No Known Activations