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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 21222
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
    okt
    -0.07
     порядку
    -0.06
    ниц
    -0.06
    _fetch
    -0.06
    .bindingNavigatorMove
    -0.06
    _props
    -0.06
    cribed
    -0.06
     '-'
    -0.06
    -summary
    -0.06
    colour
    -0.06
    POSITIVE LOGITS
    .querySelector
    0.07
    Interested
    0.07
    (canvas
    0.06
    UART
    0.06
     biçim
    0.06
    AsString
    0.06
     MICRO
    0.06
     øns
    0.06
     έχουν
    0.06
     UART
    0.06
    Activations Density 0.051%

    No Known Activations