INDEX

Explanations

:

np_max-act · gemini-2.0-flash

The neuron fires on the section‐header label “Description:” – i.e. it recognizes that metadata field header.

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

dragon

-0.07

_warning

-0.07

 department

-0.06

.color

-0.06

け

-0.06

 compromising

-0.06

_frequency

-0.06

 STORY

-0.06

 autumn

-0.06

_case

-0.06

POSITIVE LOGITS

 Spark

0.06

(gulp

0.06

Ung

0.06

举

0.06

GE

0.06

IPPING

0.06

İ

0.06

�

0.06

Til

0.06

/fa

0.06

Activations Density 0.001%

:

The neuron fires on the section‐header label “Description:” – i.e. it recognizes that metadata field header.

No Comments

No Known Activations