© 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 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. 59032
    Prev
    Next
    INDEX
    Explanations

    M

    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
    _urls
    -0.07
     Alone
    -0.06
    Illegal
    -0.06
    aukee
    -0.06
    .mvc
    -0.06
     Related
    -0.06
     sauces
    -0.06
    _holder
    -0.06
     figuring
    -0.06
     decrement
    -0.06
    POSITIVE LOGITS
     करत
    0.07
    jualan
    0.07
    imension
    0.07
     mortgage
    0.07
    trag
    0.06
    ãy
    0.06
    三个
    0.06
    .getC
    0.06
     cause
    0.06
     CGFloat
    0.06
    Activations Density 0.003%

    No Known Activations