INDEX

Explanations

descriptions and specifications

np_max-act · gemini-2.0-flash

The neuron primarily activates on numeric tokens and quantitative expressions (e.g. measurements, counts, and statistics).

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

 чуд

-0.07

 Mbps

-0.07

 ball

-0.06

chmod

-0.06

 Abby

-0.06

�

-0.06

 Qué

-0.06

 какой

-0.06

 inappropriate

-0.06

 Luke

-0.06

POSITIVE LOGITS

_mk

0.07

DropDown

0.06

 EDIT

0.06

_FINISH

0.06

[\

0.06

_frontend

0.06

angered

0.06

 BusinessException

0.06

Activations Density 0.091%

descriptions and specifications

The neuron primarily activates on numeric tokens and quantitative expressions (e.g. measurements, counts, and statistics).

No Comments

No Known Activations

descriptions and specifications

The neuron primarily activates on numeric tokens and quantitative expressions (e.g. measurements, counts, and statistics).

No Comments

No Known Activations