© 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. 62809
    Prev
    Next
    INDEX
    Explanations

    =

    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
     zf
    -0.07
     Axe
    -0.06
    RE
    -0.06
     количество
    -0.06
    atar
    -0.06
     axes
    -0.06
    defs
    -0.06
    .level
    -0.06
     towing
    -0.06
     squat
    -0.06
    POSITIVE LOGITS
    ----------------------------------------------------------------------
    0.07
    (fill
    0.07
     amusing
    0.06
     replied
    0.06
    Illustr
    0.06
    bew
    0.06
     fulfilled
    0.06
     Vladimir
    0.06
    .navigateTo
    0.06
     onHide
    0.06
    Activations Density 0.001%

    No Known Activations