INDEX

Explanations

occurrences of the word "United."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

'gc

-0.17

æĭį

-0.16

aper

-0.16

otope

-0.16

yr

-0.16

ajo

-0.16

	Copyright

-0.15

à¤ł

-0.15

ÑĢÐ¸Ð³

-0.15

Defaults

-0.14

POSITIVE LOGITS

 States

0.38

 states

0.32

-states

0.31

 STATES

0.29

States

0.27

 Nations

0.27

_states

0.26

states

0.25

 Kingdom

0.21

.states

0.21

Activations Density 0.018%

occurrences of the word "United."

No Comments

No Known Activations