INDEX

Explanations

lists

np_max-act · gemini-2.0-flash

The neuron stays silent on every input and doesn’t respond to any textual feature.

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

uses

-0.07

anlık

-0.07

ека

-0.06

Respons

-0.06

 butto

-0.06

 authService

-0.06

 цар

-0.06

orna

-0.06

 Transmit

-0.06

Work

-0.06

POSITIVE LOGITS

Never

0.07

 squarely

0.06

Tuy

0.06

İz

0.06

idd

0.06

مول

0.06

 harek

0.06

/pol

0.06

正确

0.06

(inertia

0.06

Activations Density 0.018%

lists

The neuron stays silent on every input and doesn’t respond to any textual feature.

No Comments

No Known Activations