INDEX

Explanations

genetic sequences

np_max-act · gemini-2.0-flash

The neuron reliably flags mentions of specific molecular or gene/protein names—especially multi-part identifiers like ICAM-1, IGF-II, CYP1A2, etc.

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

 bitmap

-0.06

 tutto

-0.06

iet

-0.06

úp

-0.06

 voyeur

-0.06

locks

-0.06

 glanced

-0.06

Sector

-0.06

 директор

-0.06

hait

-0.06

POSITIVE LOGITS

0.07

 decre

0.07

、

0.07

.Base

0.07

\R

0.06

ông

0.06

 عليها

0.06

Law

0.06

 stays

0.06

 rendre

0.06

Activations Density 0.034%

genetic sequences

The neuron reliably flags mentions of specific molecular or gene/protein names—especially multi-part identifiers like ICAM-1, IGF-II, CYP1A2, etc.

No Comments

No Known Activations