INDEX

Explanations

-Up

np_max-act · gemini-2.0-flash

The neuron fires on proper-name tokens—i.e. specific product, framework, game, or brand names.

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

鮮

-0.06

 Друг

-0.06

orney

-0.06

 док

-0.06

clf

-0.06

�

-0.06

仿

-0.06

YSTEM

-0.06

ational

-0.06

POSITIVE LOGITS

.enemy

0.07

_projection

0.07

 estaba

0.07

GS

0.07

	price

0.06

М

0.06

tahun

0.06

ن

0.06

_collection

0.06

.Load

0.06

Activations Density 0.336%

-Up

The neuron fires on proper-name tokens—i.e. specific product, framework, game, or brand names.

No Comments

No Known Activations