© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 72643
    Prev
    Next
    INDEX
    Explanations

    enjoy

    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
     never
    -0.06
     nowhere
    -0.06
    aptic
    -0.06
    ával
    -0.06
     Dysfunction
    -0.06
    channel
    -0.06
     الوز
    -0.06
     COD
    -0.06
    чи
    -0.06
    [vertex
    -0.06
    POSITIVE LOGITS
    ạt
    0.07
    Ln
    0.07
    clientId
    0.07
    /js
    0.07
    660
    0.06
     ภาษ
    0.06
    .…↵↵
    0.06
    イド
    0.06
    _)↵
    0.06
    _Of
    0.06
    Activations Density 0.000%

    No Known Activations