INDEX

Explanations

references to various wars and military conflicts

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

essen

-0.16

ing

-0.14

ities

-0.14

eman

-0.14

ife

-0.14

ions

-0.14

leine

-0.13

/view

-0.13

erson

-0.13

umberland

-0.13

POSITIVE LOGITS

-era

0.44

era

0.35

Era

0.33

era

0.29

-period

0.22

ERA

0.22

 period

0.19

bler

0.19

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.18

 dÃ¶nemde

0.17

Activations Density 0.033%

references to various wars and military conflicts

No Comments

No Known Activations