© 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. 27-RESID-POST-AA
    11. 11460
    Prev
    Next
    INDEX
    Explanations

    after

    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
    .struct
    -0.07
    оро
    -0.07
    ょう
    -0.06
     Chattanooga
    -0.06
    ุก
    -0.06
     france
    -0.06
    GenerationStrategy
    -0.06
     Spiral
    -0.06
     Radius
    -0.06
    ]-'
    -0.06
    POSITIVE LOGITS
     cancers
    0.06
    asley
    0.06
    HE
    0.06
     운동
    0.06
     Tir
    0.06
    (build
    0.06
     запит
    0.06
     Consult
    0.06
    UPI
    0.06
    _FORE
    0.06
    Activations Density 0.035%

    No Known Activations