INDEX

Explanations

themes related to healthcare and effective communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

áº«n

-0.16

åı¸

-0.15

ãĤĩãģĨ

-0.15

Î¸Î¿

-0.14

VML

-0.14

renders

-0.13

Ø§ÙĪØ±

-0.13

 Causes

-0.13

á»ģ

-0.13

uckle

-0.13

POSITIVE LOGITS

not

0.22

can

0.19

 goes

0.18

 shouldn

0.18

not

0.17

Not

0.17

isn

0.16

åı¯æĺ¯

0.16

 your

0.16

 will

0.16

Activations Density 0.151%

themes related to healthcare and effective communication

No Comments

No Known Activations