© 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. 127306
    Prev
    Next
    INDEX
    Explanations

    toppings

    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
     altru
    -0.07
     sql
    -0.07
    urma
    -0.07
    “How
    -0.06
    descripcion
    -0.06
    ♀
    -0.06
    !='
    -0.06
     hour
    -0.06
     궁금
    -0.06
    _CMP
    -0.06
    POSITIVE LOGITS
    LEncoder
    0.07
    격
    0.07
     размер
    0.07
    Increases
    0.07
    ги
    0.07
     Supplement
    0.07
     wear
    0.06
    мерикан
    0.06
    -effect
    0.06
    onn
    0.06
    Activations Density 0.014%

    No Known Activations