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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 124346
    Prev
    Next
    INDEX
    Explanations

    components and structure

    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
     boats
    -0.07
    运
    -0.06
    BOARD
    -0.06
     sah
    -0.06
    เหล
    -0.06
    .googleapis
    -0.06
     elbows
    -0.06
    ký
    -0.06
    chem
    -0.06
     vanished
    -0.06
    POSITIVE LOGITS
     Attendance
    0.06
     Exclude
    0.06
    _LINK
    0.06
    Scalar
    0.06
     consistent
    0.06
    .center
    0.06
    <Vector
    0.06
     queryParams
    0.06
    �
    0.06
    Tracking
    0.06
    Activations Density 0.178%

    No Known Activations