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. 15-RESID-POST-AA
    6. 21397
    Prev
    Next
    INDEX
    Explanations

    via

    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
    rolling
    -0.07
    tracted
    -0.07
     todas
    -0.06
     divis
    -0.06
     groundbreaking
    -0.06
    tractor
    -0.06
     dve
    -0.06
     میزان
    -0.06
     Кам
    -0.06
    $scope
    -0.06
    POSITIVE LOGITS
    CardContent
    0.07
    annes
    0.07
    OUNTER
    0.07
     Rotterdam
    0.06
    JJ
    0.06
    ameron
    0.06
    细胞
    0.06
     SKIP
    0.06
     HER
    0.06
    وک
    0.06
    Activations Density 0.329%

    No Known Activations