INDEX

Explanations

dependence

np_max-act · gemini-2.0-flash

The neuron selectively activates on the word “dependence” (as in “temperature dependence,” “dose dependence,” 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

Atlanta

-0.07

 gamma

-0.06

ω

-0.06

_gamma

-0.06

 Copp

-0.06

zal

-0.06

Nh

-0.06

REEN

-0.06

 kettle

-0.06

pit

-0.06

POSITIVE LOGITS

兼

0.08

Implement

0.07

hei

0.07

 Tutor

0.07

 TAKE

0.07

.ค

0.07

 groundwork

0.07

 taxed

0.07

 ImportError

0.06

asn

0.06

Activations Density 0.016%

dependence

The neuron selectively activates on the word “dependence” (as in “temperature dependence,” “dose dependence,” etc.).

No Comments

No Known Activations