INDEX

Explanations

early

np_max-act · gemini-2.0-flash

The neuron reliably activates on phrases referring to the early diagnosis or detection of a condition.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

'an

-0.07

 scripts

-0.07

 discipl

-0.06

	elif

-0.06

(protocol

-0.06

 Defines

-0.06

 Switch

-0.06

 Masters

-0.06

Controls

-0.06

xin

-0.06

POSITIVE LOGITS

 ivory

0.07

甚至

0.06

grass

0.06

	glog

0.06

报名

0.06

pem

0.06

产业

0.06

erw

0.06

 rubbed

0.06

 해당

0.06

Activations Density 0.008%

early

The neuron reliably activates on phrases referring to the early diagnosis or detection of a condition.

No Comments

No Known Activations

early

The neuron reliably activates on phrases referring to the early diagnosis or detection of a condition.

No Comments

No Known Activations