INDEX

Explanations

mathematical expressions

np_max-act · gemini-2.0-flash

This neuron identifies occurrences of a single-letter variable (especially “f”) used in arithmetic or algebraic expressions.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

	required

-0.07

Ign

-0.06

↵

-0.06

 historia

-0.06

노

-0.06

 mundo

-0.06

	ctrl

-0.06

gig

-0.06

Bond

-0.06

 контак

-0.06

POSITIVE LOGITS

лого

0.07

 heaps

0.06

.states

0.06

_Float

0.06

_produk

0.06

ivil

0.06

isclosed

0.06

reveal

0.06

HSV

0.06

-can

0.06

Activations Density 0.011%

mathematical expressions

This neuron identifies occurrences of a single-letter variable (especially “f”) used in arithmetic or algebraic expressions.

No Comments

No Known Activations