© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 108851
    Prev
    Next
    INDEX
    Explanations

    ideas

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ут
    -0.06
    .JSON
    -0.06
     akan
    -0.06
    اذا
    -0.06
     добавить
    -0.06
    -required
    -0.06
    ayah
    -0.06
    arter
    -0.06
     Schumer
    -0.06
     bizarre
    -0.06
    POSITIVE LOGITS
    _gradients
    0.08
    (dec
    0.07
     RTVF
    0.06
    >↵
    0.06
     SEND
    0.06
    vs
    0.06
    .sound
    0.06
    986
    0.06
    ULD
    0.06
     AsyncStorage
    0.06
    Activations Density 0.012%

    No Known Activations