INDEX

Explanations

information

np_max-act · gemini-2.0-flash

The neuron is specialized to pick out open‐source source‐file license headers (e.g. copyright and “Licensed under the … License” comment blocks) at the top of files.

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

Ru

-0.07

ős

-0.06

ën

-0.06

 elems

-0.06

.isRequired

-0.06

 خد

-0.06

ponce

-0.06

 perpetr

-0.06

ontvangst

-0.06

.defaults

-0.06

POSITIVE LOGITS

.Debugf

0.07

 doctoral

0.07

consulta

0.07

 unsettling

0.07

Using

0.07

 Tomáš

0.06

 Using

0.06

 Orden

0.06

.isDebugEnabled

0.06

 excited

0.06

Activations Density 0.007%

information

The neuron is specialized to pick out open‐source source‐file license headers (e.g. copyright and “Licensed under the … License” comment blocks) at the top of files.

No Comments

No Known Activations