INDEX

Explanations

phrases related to electoral processes and government decision-making

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

elor

-0.15

xing

-0.14

iol

-0.14

arshal

-0.14

LIK

-0.14

AVIS

-0.14

yles

-0.13

ãĥĩãĤ£ãĤ¢

-0.13

adies

-0.13

ÐµÑĢÐ¸Ð½

-0.13

POSITIVE LOGITS

odo

0.16

odb

0.16

another

0.15

 another

0.15

 Conclusion

0.15

âĢķ

0.15

spb

0.14

filled

0.14

outil

0.14

ocha

0.14

Activations Density 2.526%

phrases related to electoral processes and government decision-making

No Known Activations