INDEX

Explanations

providing

np_max-act · gemini-2.0-flash

The neuron detects words and phrases that describe what a resource contains or provides (e.g. contain/containing/contains information on, providing, similar).

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

 strikes

-0.06

 змож

-0.06

 struk

-0.06

isting

-0.06

Our

-0.06

 ammo

-0.06

cedes

-0.06

 suspects

-0.06

idth

-0.06

ッカー

-0.06

POSITIVE LOGITS

 điều

0.07

 MongoDB

0.07

 detections

0.07

лади

0.06

ovy

0.06

_operation

0.06

 strengthening

0.06

dropIfExists

0.06

 capitalized

0.06

_GT

0.06

Activations Density 0.060%

providing

The neuron detects words and phrases that describe what a resource contains or provides (e.g. contain/containing/contains information on, providing, similar).

No Comments

No Known Activations