INDEX

Explanations

is

np_max-act · gemini-2.0-flash

The neuron responds to common linking and explanatory words—subordinating conjunctions and auxiliary verbs (e.g. “especially,” “when,” “as,” “it,” “is,” “perpetually”) used to introduce reasons or descriptions.

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

.visual

-0.06

 seasoned

-0.06

 functionality

-0.06

 thankfully

-0.06

 auxiliary

-0.06

 MSNBC

-0.06

 жен

-0.06

 输入

-0.06

 Antique

-0.06

POSITIVE LOGITS

ooo

0.07

 dhcp

0.06

.ads

0.06

 corpse

0.06

Deployment

0.06

 Since

0.06

 cheek

0.06

Was

0.06

YPD

0.06

Ο

0.06

Activations Density 0.079%

is

The neuron responds to common linking and explanatory words—subordinating conjunctions and auxiliary verbs (e.g. “especially,” “when,” “as,” “it,” “is,” “perpetually”) used to introduce reasons or descriptions.

No Comments

No Known Activations

is

The neuron responds to common linking and explanatory words—subordinating conjunctions and auxiliary verbs (e.g. “especially,” “when,” “as,” “it,” “is,” “perpetually”) used to introduce reasons or descriptions.

No Comments

No Known Activations