© 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
    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. 60590
    Prev
    Next
    INDEX
    Explanations

    rejecting/discarding

    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
     mandate
    -0.07
     Department
    -0.06
     forecast
    -0.06
     Director
    -0.06
     Danger
    -0.06
     HW
    -0.06
    Price
    -0.06
    lications
    -0.06
    walls
    -0.06
     coz
    -0.06
    POSITIVE LOGITS
    _scheme
    0.07
     تت
    0.06
    ="../
    0.06
    Denied
    0.06
    lassen
    0.06
    uple
    0.06
    inery
    0.06
    _Timer
    0.06
     Accessed
    0.06
     gh
    0.06
    Activations Density 0.030%

    No Known Activations