INDEX

Explanations

terms related to biomedical engineering and sciences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

vely

-0.18

amt

-0.15

ãĥ³ãĥĳ

-0.15

bilder

-0.15

awns

-0.15

jam

-0.14

uktur

-0.14

 reife

-0.14

ardu

-0.14

esel

-0.14

POSITIVE LOGITS

Bi

0.25

bi

0.23

Bi

0.19

_bi

0.15

.bi

0.15

icine

0.15

ined

0.15

 engineers

0.15

 pregn

0.14

bia

0.14

Activations Density 0.033%

terms related to biomedical engineering and sciences

No Comments

No Known Activations