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. 15-RESID-POST-AA
    6. 21138
    Prev
    Next
    INDEX
    Explanations

    medications

    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
     onsite
    -0.07
    _MAPPING
    -0.07
    .font
    -0.06
     banker
    -0.06
    ingle
    -0.06
    нила
    -0.06
    /Grid
    -0.06
     investigated
    -0.06
     cartoons
    -0.06
     сам
    -0.06
    POSITIVE LOGITS
     tuples
    0.07
    (delay
    0.06
    .writeFile
    0.06
    upy
    0.06
     (![
    0.06
     дра
    0.06
    .apiUrl
    0.06
     Supern
    0.06
    prix
    0.06
     calidad
    0.06
    Activations Density 0.005%

    No Known Activations