INDEX

Explanations

Instructions/Descriptions

np_max-act · gemini-2.0-flash

The neuron fires in the context of cooking directions—spotting words that denote ingredient use and kitchen actions (e.g. “used,” “put,” “fry,” “cook,” etc.).

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

nict

-0.07

hay

-0.06

 lime

-0.06

Que

-0.06

τρο

-0.06

 Permission

-0.06

Patient

-0.06

 Reporting

-0.06

isinin

-0.06

ryn

-0.06

POSITIVE LOGITS

0.07

 TInt

0.06

 Uint

0.06

engage

0.06

형

0.06

.getInputStream

0.06

 ContentValues

0.06

 offs

0.06

 HTTPS

0.06

’)

0.05

Activations Density 0.055%

Instructions/Descriptions

The neuron fires in the context of cooking directions—spotting words that denote ingredient use and kitchen actions (e.g. “used,” “put,” “fry,” “cook,” etc.).

No Comments

No Known Activations

Instructions/Descriptions

The neuron fires in the context of cooking directions—spotting words that denote ingredient use and kitchen actions (e.g. “used,” “put,” “fry,” “cook,” etc.).

No Comments

No Known Activations