© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7814
    Prev
    Next
    INDEX
    Explanations

    Alzheimer's disease related genes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     descri
    -0.06
    享
    -0.06
    비아
    -0.06
    世
    -0.06
     surprised
    -0.06
     включа
    -0.06
     кварти
    -0.06
     Investment
    -0.06
     consisting
    -0.06
     Display
    -0.06
    POSITIVE LOGITS
    nh
    0.06
    体系
    0.06
    appid
    0.06
    >B
    0.06
    <Long
    0.06
     ortak
    0.06
     testCase
    0.06
    OTION
    0.06
    того
    0.06
    vip
    0.06
    Activations Density 0.009%

    No Known Activations