INDEX

Explanations

discovery

np_max-act · gemini-2.0-flash

The neuron flags terms and phrasing used when talking about scientific discoveries or research findings.

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

 кни

-0.06

plied

-0.06

 Symphony

-0.06

itted

-0.06

_STOCK

-0.06

歯

-0.05

 Freak

-0.05

уру

-0.05

 acknowledges

-0.05

效

-0.05

POSITIVE LOGITS

.createServer

0.09

entar

0.07

 ↵↵↵↵↵

0.07

.orig

0.07

 {{--<

0.07

 تصم

0.07

 mMap

0.07

(dirname

0.07

avy

0.06

 Activ

0.06

Activations Density 0.029%

discovery

The neuron flags terms and phrasing used when talking about scientific discoveries or research findings.

No Comments

No Known Activations