INDEX

Explanations

int

np_max-act · gemini-2.0-flash

The neuron fires on numerical data entries—especially decimal‐formatted values (e.g. R_int, T_min/max, ⟨I/σ(I)⟩, etc.) in the experimental data tables.

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

 захисту

-0.07

INA

-0.07

 Settlement

-0.07

achers

-0.07

ною

-0.06

 benzer

-0.06

 Marino

-0.06

Ful

-0.06

tones

-0.06

 occupies

-0.06

POSITIVE LOGITS

,err

0.06

"group

0.06

�

0.06

稍

0.06

wg

0.06

uous

0.06

-start

0.06

ushort

0.06

(price

0.06

 sqlSession

0.06

Activations Density 0.000%

int

The neuron fires on numerical data entries—especially decimal‐formatted values (e.g. R_int, T_min/max, ⟨I/σ(I)⟩, etc.) in the experimental data tables.

No Comments

No Known Activations