INDEX

Explanations

or

np_max-act · gemini-2.0-flash

This neuron doesn’t respond to any tokens—it remains inactive and doesn’t detect a particular pattern.

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

.Dial

-0.06

abbage

-0.06

 RestClient

-0.06

slave

-0.06

ชาว

-0.06

 đêm

-0.06

 đầu

-0.06

ilerin

-0.06

ello

-0.06

POSITIVE LOGITS

вала

0.07

_corner

0.07

	break

0.07

!'

0.06

_MEDIA

0.06

_Rect

0.06

 борь

0.06

 рамках

0.06

 mirror

0.06

후기

0.06

Activations Density 0.188%

or

This neuron doesn’t respond to any tokens—it remains inactive and doesn’t detect a particular pattern.

No Comments

No Known Activations