INDEX

Explanations

SSD

np_max-act · gemini-2.0-flash

This neuron detects mentions of storage drives—especially SSDs—whenever the text is discussing storage components.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 همسر

-0.07

Wal

-0.07

 grouped

-0.07

 trebuie

-0.07

 lavoro

-0.06

_yaml

-0.06

_CANCEL

-0.06

 rotated

-0.06

енное

-0.06

 закін

-0.06

POSITIVE LOGITS

SSD

0.08

 Exercises

0.07

 aston

0.06

 })↵↵

0.06

 Gaga

0.06

 fossil

0.06

Forms

0.06

 кг

0.06

emphasis

0.06

Activations Density 0.004%

SSD

This neuron detects mentions of storage drives—especially SSDs—whenever the text is discussing storage components.

No Comments

No Known Activations