INDEX

Explanations

terms related to empowerment and capability enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ngo

-0.16

oenix

-0.16

Ø®Ø§ÙĨÙĩ

-0.15

Ð¼Ð°Ð³Ð°

-0.15

ãĥ¼ãĥĭ

-0.14

iggins

-0.14

ÏģÎ¹Ïĥ

-0.14

$MESS

-0.14

arella

-0.14

ellen

-0.14

POSITIVE LOGITS

/disable

0.30

ment

0.18

0.16

us

0.16

0.15

/dis

0.15

Activations Density 0.025%

terms related to empowerment and capability enhancement

No Comments

No Known Activations