© 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. 104551
    Prev
    Next
    INDEX
    Explanations

    cent

    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
     Shapes
    -0.08
    rawl
    -0.07
    _RAW
    -0.07
    _App
    -0.07
     Raw
    -0.07
    Laugh
    -0.07
     Rubber
    -0.07
     Něm
    -0.07
    Remark
    -0.07
     Unidos
    -0.07
    POSITIVE LOGITS
     cent
    0.10
     Cent
    0.09
    Cent
    0.09
    -cent
    0.09
     penny
    0.07
    _cent
    0.07
     thiên
    0.07
     ·
    0.07
     CENT
    0.07
    .met
    0.07
    Activations Density 0.011%

    No Known Activations