INDEX

Explanations

code, technical documents

np_max-act · gemini-2.0-flash

The neuron is primarily detecting Windows‐specific C++ API identifiers and macros (e.g. HANDLE, CreateFile, GENERIC_READ, INVALID_HANDLE_VALUE).

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

INF

-0.07

êt

-0.07

:@

-0.06

plane

-0.06

cers

-0.06

 PLAN

-0.06

ooke

-0.06

 MediaType

-0.06

})();↵

-0.06

planes

-0.06

POSITIVE LOGITS

●

0.07

 filing

0.07

-formed

0.06

SH

0.06

 assoc

0.06

 lateinit

0.06

 uname

0.06

 slammed

0.06

 Adults

0.06

WP

0.06

Activations Density 0.293%

code, technical documents

The neuron is primarily detecting Windows‐specific C++ API identifiers and macros (e.g. HANDLE, CreateFile, GENERIC_READ, INVALID_HANDLE_VALUE).

No Comments

No Known Activations