Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 90484
    Prev
    Next
    INDEX
    Explanations

    to be

    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
     lebih
    -0.06
     McGregor
    -0.06
     被
    -0.06
    Điều
    -0.06
    ,被
    -0.06
     complexion
    -0.06
    ophobia
    -0.06
     مثلا
    -0.06
     iPod
    -0.06
     caracteres
    -0.06
    POSITIVE LOGITS
    awner
    0.07
     disciplinary
    0.07
    .nil
    0.07
    esc
    0.07
    [in
    0.07
    volatile
    0.07
     رود
    0.06
     hn
    0.06
    .accept
    0.06
    []>↵
    0.06
    Activations Density 0.171%

    No Known Activations