INDEX

Explanations

people and interactions

np_max-act · gemini-2.0-flash

The neuron responds to Portuguese-language tokens (Portuguese words and names) in the text.

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

 appeal

-0.07

촌

-0.06

Ingredient

-0.06

刺

-0.06

致

-0.06

_ASSUME

-0.06

 contiene

-0.06

良

-0.06

mej

-0.06

.packet

-0.06

POSITIVE LOGITS

(groupId

0.07

-role

0.07

OLS

0.07

.Paint

0.07

alf

0.06

cad

0.06

Univers

0.06

bas

0.06

_brightness

0.06

อนด

0.06

Activations Density 0.046%

people and interactions

The neuron responds to Portuguese-language tokens (Portuguese words and names) in the text.

No Comments

No Known Activations