INDEX

Explanations

phrases related to election outcomes and political competition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 sperma

-0.15

usercontent

-0.14

portun

-0.14

WM

-0.14

aceae

-0.13

.opts

-0.13

celik

-0.13

ìĽħ

-0.13

udiant

-0.13

orthand

-0.13

POSITIVE LOGITS

win

0.39

 winning

0.36

win

0.35

 wins

0.34

 victory

0.33

WIN

0.29

.win

0.28

 victorious

0.28

-win

0.28

 victories

0.27

Activations Density 0.208%

phrases related to election outcomes and political competition

No Comments

No Known Activations