INDEX

Explanations

topics related to public transparency and accountability in governance

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

Not in Any Lists

No Comments

Negative Logits

 Spirits

-0.14

ania

-0.14

idan

-0.14

 interiors

-0.12

cord

-0.12

 Getty

-0.12

.Interop

-0.12

zem

-0.12

 conf

-0.12

oyer

-0.12

POSITIVE LOGITS

 transparency

0.25

 information

0.23

 Transparency

0.23

 public

0.22

 transparent

0.21

 Transparent

0.20

 informational

0.20

 Information

0.20

information

0.19

Information

0.19

Activations Density 0.223%

topics related to public transparency and accountability in governance

No Comments

No Known Activations