INDEX

Explanations

sensing/recognition

np_max-act · gemini-2.0-flash

The neuron detects terms related to the recognition or sensing of molecular patterns (e.g. “sensing,” “recognition,” “detect,” “perception”).

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

ucch

-0.07

 feats

-0.07

وغ

-0.07

İT

-0.06

 göl

-0.06

 हज

-0.06

宿

-0.06

์ล

-0.06

_sig

-0.06

ugi

-0.06

POSITIVE LOGITS

 관련

0.07

 Different

0.07

.TYPE

0.07

][_

0.06

Ens

0.06

_Public

0.06

 deliberate

0.06

Red

0.06

copyright

0.06

Activations Density 0.011%

sensing/recognition

The neuron detects terms related to the recognition or sensing of molecular patterns (e.g. “sensing,” “recognition,” “detect,” “perception”).

No Comments

No Known Activations