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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 34105
    Prev
    Next
    INDEX
    Explanations

    reality tv/drama quotes

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cor
    -0.07
     vlan
    -0.06
     tiết
    -0.06
    states
    -0.06
    _proc
    -0.06
    죄
    -0.06
    .send
    -0.06
    ipelines
    -0.06
    rocket
    -0.06
    _Osc
    -0.06
    POSITIVE LOGITS
     approaches
    0.06
     contentious
    0.06
     Approval
    0.06
     تلف
    0.06
    chains
    0.06
    ，不
    0.06
     trat
    0.06
    aciones
    0.06
     hardwood
    0.06
     comprehensive
    0.06
    Activations Density 0.017%

    No Known Activations