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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102920
    Prev
    Next
    INDEX
    Explanations

    sexually explicit stories

    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
    _fm
    -0.07
     eSports
    -0.07
    "<
    -0.06
     minion
    -0.06
     [:
    -0.06
     koneč
    -0.06
    ffe
    -0.06
     RELEASE
    -0.06
     NA
    -0.06
    Uno
    -0.06
    POSITIVE LOGITS
     Assign
    0.07
    πει
    0.06
     synthesized
    0.06
     stairs
    0.06
    Code
    0.06
     dense
    0.06
     ocean
    0.06
    atonin
    0.06
    -state
    0.06
     steps
    0.06
    Activations Density 0.026%

    No Known Activations