INDEX

Explanations

Stock

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the substring “stock” in words (e.g., stock, stocking, stockpiling, Stockholm).

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

ーマ

-0.08

mam

-0.08

 wherever

-0.08

 manera

-0.08

 Mayer

-0.07

 Harm

-0.07

Radians

-0.07

 pomáh

-0.07

 Emer

-0.07

Mam

-0.07

POSITIVE LOGITS

 Stock

0.17

 stock

0.16

Stock

0.15

stock

0.14

 stocks

0.13

.stock

0.11

stocks

0.10

 STOCK

0.10

-stock

0.10

(stock

0.09

Activations Density 0.011%

Stock

This neuron activates on occurrences of the substring “stock” in words (e.g., stock, stocking, stockpiling, Stockholm).

No Comments

No Known Activations