INDEX

Explanations

.o

np_max-act · gemini-2.0-flash

The neuron fires on references to object‐file targets (the “.o” filenames and related “objs” tokens) in build/Makefile text.

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

reten

-0.08

"For

-0.07

(ver

-0.07

THOOK

-0.07

 rendre

-0.06

.WriteByte

-0.06

ienia

-0.06

 itemBuilder

-0.06

觉得

-0.06

iß

-0.06

POSITIVE LOGITS

 engines

0.08

 HttpHeaders

0.07

υκ

0.07

 telecom

0.07

 ^↵

0.06

 nine

0.06

 Breast

0.06

 ра

0.06

 Mandela

0.06

Activations Density 0.002%

.o

The neuron fires on references to object‐file targets (the “.o” filenames and related “objs” tokens) in build/Makefile text.

No Comments

No Known Activations