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. 87071
    Prev
    Next
    INDEX
    Explanations

    one

    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
    鉄道
    -0.07
     SVM
    -0.07
     کیلومتر
    -0.07
     scared
    -0.06
    strncmp
    -0.06
    BSD
    -0.06
    γραφ
    -0.06
     Baseball
    -0.06
     WR
    -0.06
     McCorm
    -0.06
    POSITIVE LOGITS
    огод
    0.08
     touches
    0.08
    лож
    0.07
     공고
    0.07
    со
    0.07
    �
    0.07
     companions
    0.07
    ôt
    0.07
    xl
    0.07
    ант
    0.07
    Activations Density 0.004%

    No Known Activations