© 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. 27505
    Prev
    Next
    INDEX
    Explanations

    External

    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
     dialect
    -0.07
    _SUP
    -0.07
     sedm
    -0.07
     Tôi
    -0.06
     Param
    -0.06
     approval
    -0.06
     topology
    -0.06
     dn
    -0.06
    ixedReality
    -0.06
    회
    -0.06
    POSITIVE LOGITS
    answered
    0.07
    ivamente
    0.07
    acted
    0.07
    ,Y
    0.06
     ofrec
    0.06
    При
    0.06
     vary
    0.06
    Pel
    0.06
    ."""
    0.06
    igung
    0.06
    Activations Density 0.003%

    No Known Activations