© 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. 27-RESID-POST-AA
    11. 21779
    Prev
    Next
    INDEX
    Explanations

    assault weapons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unused
    -0.07
     immediately
    -0.07
     getImage
    -0.06
    써
    -0.06
     guests
    -0.06
    axes
    -0.06
     Release
    -0.06
     Times
    -0.06
     USA
    -0.06
     release
    -0.06
    POSITIVE LOGITS
     tl
    0.07
     openid
    0.07
     знаю
    0.06
     mevcut
    0.06
     pří
    0.06
    nts
    0.06
     ruthless
    0.06
     форми
    0.06
    (IO
    0.06
     dilig
    0.06
    Activations Density 0.013%

    No Known Activations