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. 88710
    Prev
    Next
    INDEX
    Explanations

    Settling appeals

    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
    fork
    -0.07
     bilder
    -0.07
     природ
    -0.06
    467
    -0.06
    ",&
    -0.06
    333
    -0.06
    CJK
    -0.06
    unprocessable
    -0.06
    ctest
    -0.06
     women
    -0.06
    POSITIVE LOGITS
    ीएम
    0.07
    ây
    0.06
     Michele
    0.06
    üğ
    0.06
    Louis
    0.06
    لسل
    0.06
    ौ
    0.06
     Julie
    0.06
     talking
    0.06
     içi
    0.06
    Activations Density 0.011%

    No Known Activations