INDEX

Explanations

why

np_max-act · gemini-2.0-flash

The neuron detects when the text is offering advice, help, or guidance (e.g. “support,” “provide,” “offer”).

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

Hashtable

-0.06

 detachment

-0.06

 зам

-0.06

 multicast

-0.06

cala

-0.06

 throughput

-0.06

 interfer

-0.06

aug

-0.06

.Cluster

-0.06

"',

-0.06

POSITIVE LOGITS

why

0.14

why

0.09

 почему

0.08

Why

0.08

WHY

0.08

YL

0.07

生き

0.07

 withRouter

0.07

 reasons

0.07

RICS

0.07

Activations Density 0.015%

why

The neuron detects when the text is offering advice, help, or guidance (e.g. “support,” “provide,” “offer”).

No Comments

No Known Activations