© 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. 19-RESID-POST-AA
    6. 126798
    Prev
    Next
    INDEX
    Explanations

    email marketing

    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
    ộn
    -0.07
     veriler
    -0.07
    usaha
    -0.06
     $.
    -0.06
    rens
    -0.06
    RLF
    -0.06
     устройства
    -0.06
            			
    -0.06
    inkel
    -0.06
    學院
    -0.06
    POSITIVE LOGITS
     knocked
    0.07
     É
    0.07
    (asset
    0.06
     muddy
    0.06
     medicinal
    0.06
    (nullable
    0.06
    /em
    0.06
    BOOT
    0.06
    _FRONT
    0.06
     è
    0.06
    Activations Density 0.023%

    No Known Activations