© 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. 19-RESID-POST-AA
    11. 113695
    Prev
    Next
    INDEX
    Explanations

    URLs and names

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _boost
    -0.07
    _dropdown
    -0.07
    _Default
    -0.06
     setVisible
    -0.06
     motiv
    -0.06
    128
    -0.06
    مود
    -0.06
    闲
    -0.06
     khô
    -0.06
    _geo
    -0.06
    POSITIVE LOGITS
    unlock
    0.06
     São
    0.06
     classified
    0.06
    INGLE
    0.06
     mají
    0.06
    ró
    0.06
    ongo
    0.06
    (interface
    0.06
    ()<
    0.06
    Κ
    0.06
    Activations Density 0.005%

    No Known Activations