© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 10273
    Prev
    Next
    INDEX
    Explanations

    Theatrical performances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    后
    -0.07
     این
    -0.06
    电话
    -0.06
     улыб
    -0.06
     υπ
    -0.06
     Blackhawks
    -0.06
     Tes
    -0.06
     trẻ
    -0.06
    Chooser
    -0.06
     typing
    -0.06
    POSITIVE LOGITS
     Mandatory
    0.07
     Canadian
    0.07
    ellant
    0.07
     excellent
    0.07
    égor
    0.07
     Short
    0.06
    pis
    0.06
    cing
    0.06
     hunted
    0.06
     Наг
    0.06
    Activations Density 0.063%

    No Known Activations