INDEX

Explanations

locations

np_max-act · gemini-2.0-flash

The neuron is sensitive to mentions of storage spaces or locations (e.g. garage, shed, closet, warehouse).

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

!»

-0.07

 mand

-0.07

Л

-0.07

_CHAN

-0.06

ebilir

-0.06

 bulunan

-0.06

 khiến

-0.06

^.

-0.06

 ředitel

-0.06

()});↵

-0.06

POSITIVE LOGITS

 familiar

0.06

write

0.06

read

0.06

 retired

0.06

 unknown

0.06

 trim

0.06

 retorn

0.06

 gest

0.06

 zeit

0.06

pup

0.06

Activations Density 0.103%

locations

The neuron is sensitive to mentions of storage spaces or locations (e.g. garage, shed, closet, warehouse).

No Comments

No Known Activations