© 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
    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. 34233
    Prev
    Next
    INDEX
    Explanations

    gui

    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
    taken
    -0.07
     ink
    -0.06
    кар
    -0.06
    alf
    -0.06
    .link
    -0.06
     soukrom
    -0.06
    ıldığında
    -0.06
    olen
    -0.06
    ikal
    -0.06
    _n
    -0.06
    POSITIVE LOGITS
    GUI
    0.10
     GUI
    0.09
    .gui
    0.09
     Gui
    0.08
    GNU
    0.07
    /api
    0.07
    (GUI
    0.07
    _GUI
    0.07
     Laurie
    0.07
    Gui
    0.07
    Activations Density 0.003%

    No Known Activations