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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 83617
    Prev
    Next
    INDEX
    Explanations

    Sports seasons and teams

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .GetFileName
    -0.07
    _cells
    -0.06
    ворення
    -0.06
    inear
    -0.06
    +='
    -0.06
    ,因
    -0.06
    ‘
    -0.06
    population
    -0.06
    роме
    -0.06
    _curr
    -0.06
    POSITIVE LOGITS
     hg
    0.08
     talent
    0.07
     GDPR
    0.07
     Protector
    0.07
     getPlayer
    0.06
     Helsinki
    0.06
    roller
    0.06
    zial
    0.06
    .AdapterView
    0.06
    /full
    0.06
    Activations Density 0.000%

    No Known Activations