INDEX

Explanations

now, commas

np_max-act · gemini-2.0-flash

The neuron detects marketing‐style benefit claims – i.e. phrases in ad copy that promise a solution or extra advantage (e.g. “finally give you the extra room you need”).

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

.slider

-0.07

 attributeName

-0.07

(collection

-0.07

 только

-0.06

 attent

-0.06

_FRIEND

-0.06

 applications

-0.06

 advantage

-0.06

om

-0.06

ById

-0.06

POSITIVE LOGITS

 tanın

0.06

�

0.06

herent

0.06

ishment

0.06

ecká

0.06

наруж

0.06

 admins

0.06

पत

0.06

]."

0.06

;">↵

0.06

Activations Density 0.074%

now, commas

The neuron detects marketing‐style benefit claims – i.e. phrases in ad copy that promise a solution or extra advantage (e.g. “finally give you the extra room you need”).

No Comments

No Known Activations