INDEX

Explanations

references to healthcare professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

imei

-0.16

ãĥĥ

-0.15

 PureComponent

-0.15

à¤ªà¤¤

-0.14

æ³½

-0.14

importe

-0.14

ambio

-0.14

enie

-0.14

ä¸Ī

-0.14

arter

-0.13

POSITIVE LOGITS

ellen

0.16

ÙĪØ±Ø§ÙĨ

0.15

cri

0.14

rons

0.14

 Agree

0.14

Äĩ

0.14

ëĺĲ

0.14

rial

0.14

nal

0.14

uja

0.13

Activations Density 0.007%

references to healthcare professionals

No Comments

No Known Activations