© 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. 15-RESID-POST-AA
    11. 87143
    Prev
    Next
    INDEX
    Explanations

    Norway

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    822
    -0.07
     buck
    -0.07
    .Serve
    -0.07
    .center
    -0.06
    .InputStreamReader
    -0.06
    갔다
    -0.06
     comple
    -0.06
    ста
    -0.06
     continuity
    -0.06
     baş
    -0.06
    POSITIVE LOGITS
     Norway
    0.07
     Norwegian
    0.07
     Müslüman
    0.06
     Brendan
    0.06
     ~=
    0.06
     Heidi
    0.06
    eleri
    0.06
    replace
    0.06
     SEXP
    0.06
     ζ
    0.05
    Activations Density 0.023%

    No Known Activations