INDEX

Explanations

est

np_max-act · gemini-2.0-flash

This neuron activates on the term “anesthetized,” i.e. mentions of subjects being under anesthesia.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

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

-0.08

slow

-0.07

ilton

-0.07

.mob

-0.07

 рад

-0.07

Ol

-0.06

 ederek

-0.06

쟁

-0.06

 Canton

-0.06

.file

-0.06

POSITIVE LOGITS

 anesthesia

0.11

 antibiotic

0.07

_nth

0.07

&);↵↵

0.07

 hesitant

0.07

_hs

0.07

 SINGLE

0.07

 despre

0.07

SE

0.07

 großen

0.06

Activations Density 0.003%

est

This neuron activates on the term “anesthetized,” i.e. mentions of subjects being under anesthesia.

No Comments

No Known Activations