INDEX

Explanations

special characters

np_max-act · gemini-2.0-flash

This neuron spotlights mentions of chemical formulas or molecular species written with subscripts/superscripts (e.g., NO₂⁻, CO₂, GABA_A, Na_v).

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

ERICA

-0.07

 اکتبر

-0.07

anging

-0.07

 needless

-0.06

.tb

-0.06

oned

-0.06

OPY

-0.06

ccc

-0.06

eceği

-0.06

codile

-0.06

POSITIVE LOGITS

/shared

0.07

 вкус

0.06

	padding

0.06

 děl

0.06

 Их

0.06

.AspNet

0.06

 shifts

0.06

_FINE

0.06

än

0.06

 Accessibility

0.06

Activations Density 0.019%

special characters

This neuron spotlights mentions of chemical formulas or molecular species written with subscripts/superscripts (e.g., NO₂⁻, CO₂, GABA_A, Na_v).

No Comments

No Known Activations