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. 11-RESID-POST-AA
    6. 21178
    Prev
    Next
    INDEX
    Explanations

    Encrypted/encoded data

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Powerful
    -0.06
     knee
    -0.06
    .projects
    -0.06
    .al
    -0.06
    ि
    -0.06
    esub
    -0.06
    ongsTo
    -0.06
    oled
    -0.06
    Girl
    -0.06
    丁目
    -0.06
    POSITIVE LOGITS
     aydın
    0.07
     Lay
    0.06
     jednotliv
    0.06
    (st
    0.06
    함
    0.06
    .getPort
    0.06
    گیری
    0.06
    .lon
    0.06
     phức
    0.06
    rut
    0.06
    Activations Density 0.005%

    No Known Activations