INDEX

Explanations

contained

np_max-act · gemini-2.0-flash

The neuron activates on the legal/technical boilerplate phrase “contained in” (e.g. “contained in the …”).

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

 Champions

-0.07

[j

-0.07

 Canberra

-0.06

Gender

-0.06

debit

-0.06

_e

-0.06

 Essentials

-0.06

 champions

-0.06

Another

-0.06

.getLog

-0.06

POSITIVE LOGITS

 contained

0.11

平成

0.08

_REPLACE

0.08

 міст

0.08

 الاح

0.07

 kişinin

0.07

スペ

0.07

販

0.07

 случаев

0.07

.centerX

0.07

Activations Density 0.019%

contained

The neuron activates on the legal/technical boilerplate phrase “contained in” (e.g. “contained in the …”).

No Comments

No Known Activations

contained

The neuron activates on the legal/technical boilerplate phrase “contained in” (e.g. “contained in the …”).

No Comments

No Known Activations