INDEX

Explanations

disadvantages

np_max-act · gemini-2.0-flash

The neuron detects words that point out problems or drawbacks (e.g. defect, disadvantage, drawback) 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

 příro

-0.07

 textView

-0.06

窗

-0.06

]:
↵

-0.06

PPER

-0.06

 भग

-0.06

bows

-0.06

 мона

-0.06

NETWORK

-0.06

ruptions

-0.05

POSITIVE LOGITS

球

0.07

 Predictor

0.07

*);↵↵

0.06

 imposition

0.06

Khi

0.06

(question

0.06

잡담

0.06

 result

0.06

 göz

0.06

 Ground

0.06

Activations Density 0.012%

disadvantages

The neuron detects words that point out problems or drawbacks (e.g. defect, disadvantage, drawback) in the text.

No Comments

No Known Activations