INDEX

Explanations

rotation

np_max-act · gemini-2.0-flash

The neuron detects technical terms and proper nouns associated with gravitational physics and cosmology.

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

Negative Logits

 merit

-0.07

fragistics

-0.07

Sur

-0.06

irc

-0.06

Set

-0.06

 мала

-0.06

 éxito

-0.06

,to

-0.06

	Color

-0.06

 lookahead

-0.06

POSITIVE LOGITS

 Nationwide

0.07

 rapes

0.07

 spices

0.06

.XtraEditors

0.06

INDOW

0.06

 slowdown

0.06

รว

0.06

roller

0.06

 barrel

0.06

 Blueprint

0.06

Activations Density 0.006%

rotation

The neuron detects technical terms and proper nouns associated with gravitational physics and cosmology.

No Known Activations