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. 87024
    Prev
    Next
    INDEX
    Explanations

    ishop

    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
     труд
    -0.07
    .Debugf
    -0.07
    _Template
    -0.07
    rün
    -0.06
    'na
    -0.06
    『
    -0.06
    ("")↵
    -0.06
     Deutschland
    -0.06
    (""));↵
    -0.06
     Carla
    -0.06
    POSITIVE LOGITS
     Bishop
    0.15
     bishop
    0.12
     bishops
    0.11
    ishop
    0.09
    bishop
    0.09
     Archbishop
    0.08
     брат
    0.07
    icast
    0.07
    /block
    0.07
    bios
    0.07
    Activations Density 0.003%

    No Known Activations