© 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 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. 110053
    Prev
    Next
    INDEX
    Explanations

    them

    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
    âu
    -0.06
    보고
    -0.06
    ителя
    -0.06
    คราม
    -0.05
    इस
    -0.05
    보다
    -0.05
    理解
    -0.05
     knitting
    -0.05
    手に
    -0.05
     변경
    -0.05
    POSITIVE LOGITS
    _maps
    0.08
     listed
    0.07
    _examples
    0.07
    enticated
    0.07
    MBProgressHUD
    0.07
     Locate
    0.07
    (description
    0.07
     selecion
    0.07
     distinguished
    0.07
    StartupScript
    0.07
    Activations Density 0.000%

    No Known Activations