© 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. 19-RESID-POST-AA
    6. 99619
    Prev
    Next
    INDEX
    Explanations

    runner

    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
    播放
    -0.07
    /topics
    -0.07
     changed
    -0.06
    IDE
    -0.06
    総
    -0.06
     hạ
    -0.06
    ‌ال
    -0.06
     cuatro
    -0.06
     вони
    -0.06
    (food
    -0.06
    POSITIVE LOGITS
    _SEL
    0.07
     hepatitis
    0.07
    (reinterpret
    0.07
     Kin
    0.06
    ="",
    0.06
    viders
    0.06
    gener
    0.06
    contres
    0.06
    .pnl
    0.06
     klim
    0.06
    Activations Density 0.094%

    No Known Activations