INDEX

Explanations

201

np_max-act · gemini-2.0-flash

This neuron is detecting four-digit year numbers (i.e., the year tokens in datelines).

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

互

-0.06

xAE

-0.06

_generation

-0.06

(hr

-0.06

σίας

-0.06

 geldi

-0.06

 horrend

-0.06

 vydání

-0.06

 harc

-0.06

 nightlife

-0.06

POSITIVE LOGITS

 Require

0.07

 define

0.06

violent

0.06

_tables

0.06

 Brake

0.06

listed

0.06

 Glide

0.06

AbsolutePath

0.06

 localhost

0.06

 Leaves

0.06

Activations Density 0.003%

201

This neuron is detecting four-digit year numbers (i.e., the year tokens in datelines).

No Comments

No Known Activations

201

This neuron is detecting four-digit year numbers (i.e., the year tokens in datelines).

No Comments

No Known Activations