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. 3-RESID-POST-AA
    6. 94746
    Prev
    Next
    INDEX
    Explanations

    consultation

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    168
    -0.07
     Margin
    -0.07
    dst
    -0.07
     Domestic
    -0.06
     взрос
    -0.06
     temporarily
    -0.06
     Seems
    -0.06
     tires
    -0.06
     Apocalypse
    -0.06
     rebuild
    -0.06
    POSITIVE LOGITS
     consulta
    0.10
     consultar
    0.09
    Consulta
    0.09
    consulta
    0.08
     consulted
    0.08
    서울
    0.07
    úsqueda
    0.07
    사항
    0.06
    iero
    0.06
     Consultants
    0.06
    Activations Density 0.013%

    No Known Activations