INDEX

Explanations

is

np_max-act · gemini-2.0-flash

This neuron detects floating-point numeric scores (decimal numbers like “0.324…” or “0.543…”).

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

 toolkit

-0.07

 pulled

-0.06

HD

-0.06

 Erotic

-0.06

OURS

-0.06

 magnificent

-0.06

Retail

-0.06

chief

-0.06

gov

-0.06

 Brut

-0.06

POSITIVE LOGITS

.cycle

0.07

.ResultSet

0.06

[cur

0.06

 رم

0.06

,time

0.06

#region

0.06

 dependable

0.06

 сал

0.06

isLoading

0.06

.con

0.06

Activations Density 0.012%

is

This neuron detects floating-point numeric scores (decimal numbers like “0.324…” or “0.543…”).

No Comments

No Known Activations