INDEX

Explanations

11

np_max-act · gemini-2.0-flash

The neuron detects square‐root expressions (instances of “sqrt(… )”) in mathematical formulas.

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

。在

-0.07

国際

-0.06

กรรมการ

-0.06

"`

-0.06

/]

-0.06

 scared

-0.06

TRY

-0.06

요

-0.06

-enable

-0.06

_td

-0.06

POSITIVE LOGITS

 playable

0.07

 Cheng

0.07

.”↵↵↵↵

0.06

 beş

0.06

.SetActive

0.06

 Πέ

0.06

 Billing

0.06

 microwave

0.06

 ACCEPT

0.06

 placed

0.06

Activations Density 0.002%

11

The neuron detects square‐root expressions (instances of “sqrt(… )”) in mathematical formulas.

No Comments

No Known Activations