INDEX

Explanations

additional quantities

np_max-act · gemini-2.0-flash

The neuron fires on words that signal higher quantities or increases—especially the comparative/quantifier “more.”

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

 Surv

-0.08

AUX

-0.07

planation

-0.06

 formatted

-0.06

 газ

-0.06

ิลล

-0.06

meyi

-0.06

enou

-0.06

LW

-0.06

_UL

-0.06

POSITIVE LOGITS

ologies

0.06

 gall

0.06

 echoing

0.06

checking

0.06

(outfile

0.06

 Appropri

0.06

 kotlin

0.06

="./

0.06

۳۶

0.06

 رسم

0.06

Activations Density 0.022%

additional quantities

The neuron fires on words that signal higher quantities or increases—especially the comparative/quantifier “more.”

No Comments

No Known Activations

additional quantities

The neuron fires on words that signal higher quantities or increases—especially the comparative/quantifier “more.”

No Comments

No Known Activations