INDEX

Explanations

ptr

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of “lens” or “Lenses” identifiers or keywords—i.e. it picks out uses of lens-related terms in the code.

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

.Rows

-0.07

>t

-0.07

_ts

-0.07

²

-0.07

tatus

-0.06

lua

-0.06

Classes

-0.06

Lic

-0.06

doi

-0.06

III

-0.06

POSITIVE LOGITS

 departing

0.07

(PATH

0.07

 researched

0.07

ESH

0.07

_FIELD

0.06

 enlarge

0.06

 administrators

0.06

_THAT

0.06

//*[@

0.06

"};
↵

0.06

Activations Density 0.000%

ptr

The neuron fires on occurrences of “lens” or “Lenses” identifiers or keywords—i.e. it picks out uses of lens-related terms in the code.

No Comments

No Known Activations