© 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. 23053
    Prev
    Next
    INDEX
    Explanations

    eq

    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
     criticisms
    -0.07
    _Free
    -0.07
     Difference
    -0.06
     поверхность
    -0.06
    254
    -0.06
    参
    -0.06
    珍
    -0.06
     количества
    -0.06
    +[
    -0.06
     HOUR
    -0.06
    POSITIVE LOGITS
     authDomain
    0.07
    річ
    0.06
     نگهداری
    0.06
    phalt
    0.06
     Россий
    0.06
     kunt
    0.06
    ynchronously
    0.06
    ched
    0.06
     möchte
    0.06
    _workflow
    0.06
    Activations Density 0.002%

    No Known Activations