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. 10653
    Prev
    Next
    INDEX
    Explanations

    Sor

    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
    查看
    -0.07
     partes
    -0.07
    drink
    -0.07
    х
    -0.06
     Кан
    -0.06
    GLOBAL
    -0.06
    �i
    -0.06
    /public
    -0.06
    sizes
    -0.06
     struk
    -0.06
    POSITIVE LOGITS
     Net
    0.07
    [Math
    0.07
     Talk
    0.06
    (bucket
    0.06
     Star
    0.06
     DS
    0.06
    иплом
    0.06
     ffi
    0.06
    -shot
    0.06
    (Math
    0.06
    Activations Density 0.456%

    No Known Activations