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. 7-RESID-POST-AA
    6. 71967
    Prev
    Next
    INDEX
    Explanations

    gaming

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourse
    -0.07
     nom
    -0.06
    arg
    -0.06
     PHONE
    -0.06
    mma
    -0.06
    (Point
    -0.06
    367
    -0.06
     Shaman
    -0.06
    urance
    -0.06
    duced
    -0.06
    POSITIVE LOGITS
     उनक
    0.07
     Pessoa
    0.06
    (sem
    0.06
     TInt
    0.06
    .consumer
    0.06
     щось
    0.06
    нюю
    0.06
    .HorizontalAlignment
    0.06
     ساختمان
    0.06
    .minimum
    0.06
    Activations Density 0.056%

    No Known Activations