INDEX

Explanations

car models

np_max-act · gemini-2.0-flash

The neuron detects numeric date tokens—especially four-digit years and other numbers indicating production or model years.

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

 baked

-0.07

 Missouri

-0.07

 AudioManager

-0.07

 revealed

-0.07

ATED

-0.07

 Forces

-0.06

cba

-0.06

ated

-0.06

Commit

-0.06

ranges

-0.06

POSITIVE LOGITS

Usually

0.07

[["

0.06

 зан

0.06

��

0.06

>('

0.06

 โรง

0.06

 zápas

0.06

ického

0.06

strconv

0.06

 karşısında

0.06

Activations Density 0.017%

car models

The neuron detects numeric date tokens—especially four-digit years and other numbers indicating production or model years.

No Comments

No Known Activations