INDEX

Explanations

2

np_max-act · gemini-2.0-flash

The neuron detects explicit references to OSI network layer labels (e.g. “layer 2,” “layer 3”) in the text.

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

orida

-0.07

cosity

-0.07

OTOR

-0.07

.serialize

-0.06

服务器

-0.06

.MixedReality

-0.06

machine

-0.06

oid

-0.06

monitor

-0.06

_Request

-0.06

POSITIVE LOGITS

秋

0.07

 informational

0.06

 Clarkson

0.06

 realm

0.06

 μά

0.06

	Spring

0.06

rtn

0.06

ώ

0.06

 Barang

0.06

(=

0.06

Activations Density 0.001%

2

The neuron detects explicit references to OSI network layer labels (e.g. “layer 2,” “layer 3”) in the text.

No Comments

No Known Activations