INDEX

Explanations

phrases indicating relationships and obligations involving care and responsibility, particularly in a legal or medical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

boo

-0.17

ruk

-0.14

ëĭĪëĭ¤

-0.14

 gerne

-0.14

 Bootstrap

-0.14

boo

-0.14

ving

-0.13

leton

-0.13

 attribution

-0.13

áº£nh

-0.13

POSITIVE LOGITS

ãĥ³ãĤ¯

0.18

auer

0.17

icaid

0.15

nun

0.15

alf

0.15

 Laurent

0.15

áº£i

0.14

Lit

0.14

VOKE

0.14

ousse

0.14

Activations Density 0.944%

phrases indicating relationships and obligations involving care and responsibility, particularly in a legal or medical context

No Comments

No Known Activations