© 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. 27957
    Prev
    Next
    INDEX
    Explanations

    code repositories/URLs

    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
     squads
    -0.07
    ">*</
    -0.07
    //===
    -0.06
     squad
    -0.06
    	account
    -0.06
    SEA
    -0.06
     bizi
    -0.06
     التو
    -0.06
    	Default
    -0.06
    -0.06
    POSITIVE LOGITS
     цін
    0.06
    ্�
    0.06
     раді
    0.06
    _encrypt
    0.06
    Ps
    0.06
    ша
    0.06
    _pr
    0.06
    ш
    0.06
    veřej
    0.06
    ักร
    0.06
    Activations Density 0.062%

    No Known Activations