Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87073
    Prev
    Next
    INDEX
    Explanations

    ographic

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ₹
    -0.08
     Soul
    -0.07
    (L
    -0.07
    Castle
    -0.06
     let
    -0.06
    Ell
    -0.06
     Castle
    -0.06
    ul
    -0.06
     soul
    -0.06
     PUS
    -0.06
    POSITIVE LOGITS
    ographic
    0.09
    GRAPH
    0.09
    ography
    0.08
    ograph
    0.08
    ogra
    0.08
    ideographic
    0.08
    ogr
    0.08
    ográf
    0.08
    егра
    0.08
    ограф
    0.08
    Activations Density 0.014%

    No Known Activations