Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 81191
    Prev
    Next
    INDEX
    Explanations

    Adhesives and sealants

    np_max-act · gemini-2.0-flash
    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
    _widget
    -0.07
     raped
    -0.07
    Card
    -0.07
    _runs
    -0.07
    Sensitive
    -0.06
    View
    -0.06
    _COMPLETED
    -0.06
     Nová
    -0.06
    Domains
    -0.06
    Cisco
    -0.06
    POSITIVE LOGITS
     μέχρι
    0.07
    heiten
    0.07
    -th
    0.06
     пох
    0.06
    unless
    0.06
     cambio
    0.06
    lus
    0.06
    ứa
    0.06
    ни
    0.06
    _expect
    0.06
    Activations Density 0.003%

    No Known Activations