INDEX

Explanations

ra

np_max-act · gemini-2.0-flash

This neuron detects pieces of systematic chemical nomenclature—especially IUPAC prefixes and ring‐structure fragments (e.g. “dinitro,” “tetra,” “diazacyclo”).

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

 dynamics

-0.07

تها

-0.07

 whoever

-0.06

(settings

-0.06

 neighbors

-0.06

 Apparently

-0.06

 james

-0.06

 agenda

-0.06

 MOTOR

-0.06

 women

-0.06

POSITIVE LOGITS

 χρησιμοποι

0.07

_STENCIL

0.07

 привед

0.06

Main

0.06

 GridBagConstraints

0.06

imonial

0.06

NORMAL

0.06

控

0.06

 techno

0.06

ả

0.06

Activations Density 0.011%

ra

This neuron detects pieces of systematic chemical nomenclature—especially IUPAC prefixes and ring‐structure fragments (e.g. “dinitro,” “tetra,” “diazacyclo”).

No Comments

No Known Activations