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. 15-RESID-POST-AA
    6. 128207
    Prev
    Next
    INDEX
    Explanations

    :

    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
     gọn
    -0.08
     资
    -0.07
    (t
    -0.07
    という
    -0.07
    fte
    -0.07
    getConnection
    -0.07
    muştur
    -0.06
     fj
    -0.06
    -days
    -0.06
    (read
    -0.06
    POSITIVE LOGITS
     ERC
    0.07
     Massachusetts
    0.07
     charcoal
    0.06
    trecht
    0.06
     YEARS
    0.06
     भर
    0.06
    /ui
    0.06
     Lange
    0.06
     obst
    0.06
     chúng
    0.06
    Activations Density 0.004%

    No Known Activations