INDEX

Explanations

Corona/Coronary

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

hound

-0.06

 Language

-0.06

week

-0.06

難

-0.06

 Cathy

-0.06

러

-0.06

.medium

-0.06

SD

-0.06

POSITIVE LOGITS

 Coron

0.09

roma

0.08

 Goldman

0.08

 Corona

0.07

iron

0.07

alta

0.07

 coron

0.07

 orbs

0.07

orno

0.07

oningen

0.07

Activations Density 0.002%

Corona/Coronary

No Comments

No Known Activations