INDEX

Explanations

Biographies

np_max-act · gemini-2.0-flash

This neuron detects verbs that mark significant career or life transitions (e.g. joined, left, returned, disappeared).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Duty

-0.07

\controllers

-0.07

 rolled

-0.06

#from

-0.06

'('

-0.06

UTDOWN

-0.06

期待

-0.06

,item

-0.06

てい

-0.06

ับความ

-0.06

POSITIVE LOGITS

 mænd

0.06

 Adult

0.06

Social

0.06

(exp

0.06

 computation

0.06

=u

0.06

+k

0.06

-development

0.06

_CANCEL

0.06

fluid

0.06

Activations Density 0.024%

Biographies

This neuron detects verbs that mark significant career or life transitions (e.g. joined, left, returned, disappeared).

No Comments

No Known Activations

Biographies

This neuron detects verbs that mark significant career or life transitions (e.g. joined, left, returned, disappeared).

No Comments

No Known Activations