INDEX

Explanations

Research studies

np_max-act · gemini-2.0-flash

The neuron responds to words signaling a paper’s stated aim or method—verbs and phrases like “objective,” “study,” “examines,” “we explored,” and “investigated” that introduce the research purpose.

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

važ

-0.06

_female

-0.06

venile

-0.06

 validity

-0.06

 deliveries

-0.06

 patches

-0.06

 newborn

-0.06

 anchor

-0.06

 MOUSE

-0.06

tap

-0.06

POSITIVE LOGITS

.isArray

0.06

 ViewData

0.06

(CharSequence

0.06

 Vlad

0.06

.onNext

0.06

olves

0.06

 amendments

0.06

Dh

0.06

 tieten

0.06

 Emit

0.06

Activations Density 0.135%

Research studies

The neuron responds to words signaling a paper’s stated aim or method—verbs and phrases like “objective,” “study,” “examines,” “we explored,” and “investigated” that introduce the research purpose.

No Comments

No Known Activations