INDEX

Explanations

terms related to the brain and its functions in both health and illness contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÑĢÑĥÐ±

-0.15

imas

-0.14

 Extr

-0.14

é®®

-0.14

arme

-0.14

Pel

-0.14

hip

-0.14

 strav

-0.14

.foundation

-0.14

Tos

-0.13

POSITIVE LOGITS

eren

0.16

-wide

0.15

anda

0.15

/org

0.15

0.14

/body

0.14

æºª

0.14

ç§Ģ

0.14

\CMS

0.14

-employed

0.13

Activations Density 0.084%

terms related to the brain and its functions in both health and illness contexts

No Comments

No Known Activations