© 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. 19-RESID-POST-AA
    11. 84360
    Prev
    Next
    INDEX
    Explanations

    Arguments and opinions

    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
     insp
    -0.07
    Recipe
    -0.07
     Bast
    -0.07
    .addRow
    -0.06
    iculo
    -0.06
     Coastal
    -0.06
    Fields
    -0.06
     Alonso
    -0.06
    _quantity
    -0.06
    .generic
    -0.06
    POSITIVE LOGITS
    non
    0.07
    ť
    0.06
    Yes
    0.06
    (AL
    0.06
    enschaft
    0.06
    ，该
    0.06
    pac
    0.06
    Vý
    0.06
    溶
    0.06
    .UserService
    0.05
    Activations Density 0.093%

    No Known Activations