© 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. 123987
    Prev
    Next
    INDEX
    Explanations

    protocol

    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
     Hicks
    -0.08
    esinin
    -0.07
     Howe
    -0.06
    Orientation
    -0.06
     Thorn
    -0.06
     pově
    -0.06
    NY
    -0.06
     Gaussian
    -0.06
    hib
    -0.06
     ổn
    -0.06
    POSITIVE LOGITS
    STRUCTOR
    0.06
    =.
    0.06
    :param
    0.06
    ƒ
    0.06
     لكل
    0.06
     calculations
    0.06
    裝
    0.06
    :"
    0.06
    .bg
    0.06
    Really
    0.06
    Activations Density 0.001%

    No Known Activations