© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 46771
    Prev
    Next
    INDEX
    Explanations

    new

    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
     phim
    -0.07
     standoff
    -0.06
     peek
    -0.06
     música
    -0.06
    Checkbox
    -0.06
     HUGE
    -0.06
     판
    -0.06
    िष
    -0.06
     `;↵
    -0.06
    _PRED
    -0.06
    POSITIVE LOGITS
     conditioner
    0.07
    стит
    0.07
     sanction
    0.07
     checker
    0.06
     onay
    0.06
    (contract
    0.06
    ђ
    0.06
    のお
    0.06
     snad
    0.06
     ดาว
    0.06
    Activations Density 0.060%

    No Known Activations