INDEX

Explanations

of many

np_max-act · gemini-2.0-flash

This neuron activates on the phrase “a variety of,” essentially detecting the word “variety” (often in the context “a variety of …”).

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

 amort

-0.07

 bottled

-0.07

']:↵

-0.07

Within

-0.06

 删除

-0.06

 díky

-0.06

，因为

-0.06

"]:↵

-0.06

 circumstance

-0.06

 vinegar

-0.06

POSITIVE LOGITS

(pdev

0.07

WR

0.07

UnderTest

0.07

-meta

0.06

icator

0.06

>[

0.06

ATL

0.06

BC

0.06

■■

0.06

wg

0.05

Activations Density 0.026%

of many

This neuron activates on the phrase “a variety of,” essentially detecting the word “variety” (often in the context “a variety of …”).

No Comments

No Known Activations