INDEX

Explanations

mass

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “mass” (or “Mass”)—including when it appears as a standalone token or at the start of compound terms.

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

Dit

-0.07

-chair

-0.07

cyn

-0.07

 Friedrich

-0.07

 Putin

-0.07

Vue

-0.07

proper

-0.07

.done

-0.07

čit

-0.07

 optimum

-0.07

POSITIVE LOGITS

 mass

0.17

 Mass

0.16

Mass

0.13

 MASS

0.13

mass

0.12

 масс

0.10

_mass

0.10

SS

0.10

.mass

0.10

 masses

0.09

Activations Density 0.014%

mass

This neuron activates on occurrences of the word “mass” (or “Mass”)—including when it appears as a standalone token or at the start of compound terms.

No Comments

No Known Activations