INDEX

Explanations

!"

np_max-act · gemini-2.0-flash

This neuron specializes in detecting the literal “Hello, World!” greeting string in example 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 PREFIX

-0.07

Mapper

-0.07

 geography

-0.07

grey

-0.06

 setEmail

-0.06

 measurable

-0.06

 holog

-0.06

 conveniently

-0.06

الی

-0.06

(angle

-0.06

POSITIVE LOGITS

 uzav

0.07

 па

0.07

 İngiliz

0.07

Sı

0.07

 citas

0.07

цієн

0.07

Normals

0.06

_PY

0.06

맞

0.06

 İlk

0.06

Activations Density 0.029%

!"

This neuron specializes in detecting the literal “Hello, World!” greeting string in example code.

No Comments

No Known Activations