INDEX

Explanations

Names and identifiers

np_max-act · gemini-2.0-flash

The neuron never fires (all its activations are zero), so it isn’t detecting any consistent feature in the text.

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

↵

-0.07

|↵

-0.07

xbe

-0.06

 presses

-0.06

Kids

-0.06

 camper

-0.06

fprintf

-0.06

 realistic

-0.06

 pulse

-0.06

	total

-0.06

POSITIVE LOGITS

Exclude

0.06

CanBe

0.06

adden

0.06

 فرانسه

0.06

 Meteor

0.06

 coer

0.06

 churn

0.06

 Ders

0.06

 sàng

0.06

/Index

0.06

Activations Density 0.046%

Names and identifiers

The neuron never fires (all its activations are zero), so it isn’t detecting any consistent feature in the text.

No Comments

No Known Activations