INDEX

Explanations

patients

np_max-act · gemini-2.0-flash

The neuron primarily activates on numeric tokens and measurements (e.g. dosages, sample sizes, percentages, p‐values), effectively finding quantitative data 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SqlDbType

-0.07

.mongodb

-0.07

ActivityIndicatorView

-0.07

opleft

-0.07

TOK

-0.07

GLIGENCE

-0.07

"}},↵

-0.06

Videos

-0.06

/blob

-0.06

)),

-0.06

POSITIVE LOGITS

──

0.06

 epidemic

0.06

.n

0.06

力的

0.06

estate

0.06

.cols

0.06

идент

0.06

.life

0.05

日に

0.05

лей

0.05

Activations Density 0.029%

patients

The neuron primarily activates on numeric tokens and measurements (e.g. dosages, sample sizes, percentages, p‐values), effectively finding quantitative data in the text.

No Comments

No Known Activations