INDEX

Explanations

rate

np_max-act · gemini-2.0-flash

This neuron activates on mentions of “rate” (especially in financial contexts like interest‐rate and mortgage‐rate 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gossip

-0.06

PEM

-0.06

PostBack

-0.06

 Nuclear

-0.06

chen

-0.06

 Patron

-0.06

영

-0.06

 UNIX

-0.06

 cookbook

-0.06

.AutoSizeMode

-0.06

POSITIVE LOGITS

erspective

0.07

same

0.07

.So

0.07

 ventured

0.07

(hr

0.06

.Duration

0.06

 rate

0.06

摩

0.06

jr

0.06

 underrated

0.06

Activations Density 0.004%

rate

This neuron activates on mentions of “rate” (especially in financial contexts like interest‐rate and mortgage‐rate terms).

No Comments

No Known Activations