INDEX

Explanations

significantly

np_max-act · gemini-2.0-flash

This neuron detects reported statistical test values (e.g. t-statistics or p-values) in the text.

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

Lat

-0.07

 рецеп

-0.07

 sổ

-0.06

Gdk

-0.06

LRV

-0.06

LAT

-0.06

.persistent

-0.06

 пис

-0.06

 قسمت

-0.06

 sunset

-0.06

POSITIVE LOGITS

uably

0.07

 adorned

0.06

 Credential

0.06

ilmington

0.06

 Jungle

0.06

PMC

0.06

명의

0.06

.cli

0.06

ButtonDown

0.06

 ainsi

0.06

Activations Density 0.012%

significantly

This neuron detects reported statistical test values (e.g. t-statistics or p-values) in the text.

No Comments

No Known Activations