INDEX

Explanations

deficiency

np_max-act · gemini-2.0-flash

The neuron activates on mentions of a deficiency—especially nutritional or biochemical deficiencies—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

Yap

-0.07

 rotation

-0.07

-0.06

 boat

-0.06

 gesture

-0.06

响

-0.06

.djang

-0.06

 Spiele

-0.06

 Palestine

-0.06

transform

-0.06

POSITIVE LOGITS

 deficiency

0.13

 deficient

0.12

 deficit

0.11

 deficiencies

0.10

 deficits

0.08

 shortages

0.07

 shortage

0.07

inson

0.07

odef

0.07

MF

0.07

Activations Density 0.007%

deficiency

The neuron activates on mentions of a deficiency—especially nutritional or biochemical deficiencies—in the text.

No Comments

No Known Activations