INDEX

Explanations

X or GTX

np_max-act · gemini-2.0-flash

The neuron fires on tokens that are parts of graphics‐card model names (e.g. “RTX,” “GTX,” numeric model designations).

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

 KeyEvent

-0.06

 jente

-0.06

 shear

-0.06

kind

-0.06

Pad

-0.06

_sel

-0.06

ZONE

-0.06

.Card

-0.06

ANJI

-0.06

�

-0.06

POSITIVE LOGITS

ัท

0.07

国際

0.07

 Trial

0.07

McL

0.06

Subscribe

0.06

atever

0.06

ई

0.06

ual

0.06

 Highlights

0.06

 titten

0.06

Activations Density 0.001%

X or GTX

The neuron fires on tokens that are parts of graphics‐card model names (e.g. “RTX,” “GTX,” numeric model designations).

No Comments

No Known Activations