INDEX

Explanations

terms related to autoimmune diseases and their effects

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

 cancer

-0.16

yan

-0.15

 Shelf

-0.15

 Aspen

-0.15

 tumors

-0.15

é

-0.14

 sexual

-0.14

 Cancer

-0.14

.Operator

-0.14

åĬ

-0.14

POSITIVE LOGITS

 autoimmune

0.26

 auto

0.25

 Auto

0.24

auto

0.22

Rhe

0.22

/auto

0.21

Auto

0.21

 flare

0.20

 inflamm

0.19

:auto

0.19

Activations Density 0.034%

terms related to autoimmune diseases and their effects

No Comments

No Known Activations