© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 12955
    Prev
    Next
    INDEX
    Explanations

    sharing, responsibility

    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
     infantry
    -0.06
     engulf
    -0.06
    وقف
    -0.06
    一次
    -0.06
    ######↵
    -0.06
    GeneratedValue
    -0.06
    {'
    -0.06
     volum
    -0.06
     Ezek
    -0.06
     forgive
    -0.06
    POSITIVE LOGITS
    /file
    0.07
    ctype
    0.06
    course
    0.06
    357
    0.06
     Grande
    0.06
    _ALREADY
    0.06
    contri
    0.06
    Delivery
    0.06
    urniture
    0.06
     STDOUT
    0.06
    Activations Density 0.001%

    No Known Activations