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. 9786
    Prev
    Next
    INDEX
    Explanations

    ATP

    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
     说
    -0.07
    Pokud
    -0.07
     เล
    -0.07
     confess
    -0.06
    leştir
    -0.06
    *w
    -0.06
    manı
    -0.06
     jaar
    -0.06
    ToAdd
    -0.06
    رو
    -0.06
    POSITIVE LOGITS
    ":[
    0.07
    Runner
    0.07
    ¢
    0.06
     manual
    0.06
    FLOAT
    0.06
    .gradient
    0.06
    [Math
    0.06
     NASA
    0.06
    โม
    0.06
    feature
    0.06
    Activations Density 0.069%

    No Known Activations