INDEX

Explanations

phrases related to decision-making and moral dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

istik

-0.17

-0.15

rea

-0.15

 kabil

-0.14

itespace

-0.14

errick

-0.14

alu

-0.14

 Wagner

-0.14

atik

-0.14

alist

-0.13

POSITIVE LOGITS

wei

0.15

eus

0.15

'gc

0.15

)(*

0.15

.localized

0.14

/Index

0.14

hsi

0.14

ãĥ£

0.14

moc

0.14

UTILITY

0.14

Activations Density 0.309%

phrases related to decision-making and moral dilemmas

No Comments

No Known Activations