INDEX

Explanations

code data structures

np_max-act · gemini-2.0-flash

The neuron detects JSON object property names (and their accompanying values) such as “title,” “duration,” and “cta.”

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

 Wash

-0.07

 أحمد

-0.07

 agli

-0.07

 Venezuelan

-0.07

Partner

-0.07

 food

-0.07

 القد

-0.07

itized

-0.07

 edible

-0.06

multiline

-0.06

POSITIVE LOGITS

nä

0.06

-app

0.06

)/(

0.06

 veces

0.06

 freak

0.06

 domic

0.06

 informatie

0.06

 fick

0.06

-Control

0.06

인데

0.06

Activations Density 0.057%

code data structures

The neuron detects JSON object property names (and their accompanying values) such as “title,” “duration,” and “cta.”

No Comments

No Known Activations