INDEX

Explanations

K

np_max-act · gemini-2.0-flash

This neuron fires on the LaTeX‐style occurrences of “K” (especially subscripted Kₙ or Kᵢ) in formulas—i.e. it recognizes references to Kravchuk-polynomial notation.

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

_scalar

-0.07

profiles

-0.06

predict

-0.06

;


↵

-0.06

усти

-0.06

Elem

-0.06

 řek

-0.06

 بالم

-0.06

 جنگ

-0.06

POSITIVE LOGITS

.SizeF

0.07

 hikes

0.06

lv

0.06

ินการ

0.06

"title

0.06

ST

0.06

.simpleButton

0.06

LV

0.06

expire

0.06

porate

0.06

Activations Density 0.021%

K

This neuron fires on the LaTeX‐style occurrences of “K” (especially subscripted Kₙ or Kᵢ) in formulas—i.e. it recognizes references to Kravchuk-polynomial notation.

No Comments

No Known Activations

K

This neuron fires on the LaTeX‐style occurrences of “K” (especially subscripted Kₙ or Kᵢ) in formulas—i.e. it recognizes references to Kravchuk-polynomial notation.

No Comments

No Known Activations