INDEX

Explanations

terms related to biological processes and infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ONTAL

-0.16

ä¸¸

-0.15

zell

-0.15

 reels

-0.15

ÐµÑĢÐ°Ð¿

-0.14

pest

-0.14

ë£¡

-0.14

 Bers

-0.14

icie

-0.14

.flatten

-0.14

POSITIVE LOGITS

 infections

0.36

 infection

0.36

 bacterial

0.31

 bacteria

0.27

fections

0.25

 bacter

0.24

fection

0.22

 infected

0.22

 infect

0.22

 Gram

0.22

Activations Density 0.094%

terms related to biological processes and infections

No Comments

No Known Activations