© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54143
    Prev
    Next
    INDEX
    Explanations

    announcements and notifications

    np_max-act · gemini-2.0-flash

    This neuron detects words that signal scheduled updates or announcements of upcoming events or actions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    grades
    -0.07
     Ogre
    -0.06
    ampoline
    -0.06
     Money
    -0.06
    	fun
    -0.06
     Mek
    -0.06
     Duncan
    -0.06
     BUF
    -0.06
    ワー
    -0.06
     MONEY
    -0.06
    POSITIVE LOGITS
    (chalk
    0.07
     cock
    0.07
    :<?
    0.06
    ("("
    0.06
    contres
    0.06
     rencontres
    0.06
    ự
    0.06
    /man
    0.06
    ώς
    0.06
    ého
    0.06
    Activations Density 0.024%

    No Known Activations