© 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 EvalsExportsinterp-engineNEWAPI 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. 92816
    Prev
    Next
    INDEX
    Explanations

    When

    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
     és
    -0.07
    undo
    -0.06
    ypsy
    -0.06
    #region
    -0.06
     Его
    -0.06
     Fin
    -0.06
    ***↵
    -0.06
     getContentPane
    -0.06
    zer
    -0.06
     gü
    -0.06
    POSITIVE LOGITS
    /User
    0.06
    Narr
    0.06
    ODE
    0.06
     кури
    0.06
    .Qu
    0.06
    .Service
    0.06
     WHILE
    0.06
     spear
    0.06
    alf
    0.06
    was
    0.06
    Activations Density 0.046%

    No Known Activations