© 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. 47234
    Prev
    Next
    INDEX
    Explanations

    rose

    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
    ibur
    -0.07
     Municipal
    -0.07
     whim
    -0.06
    vider
    -0.06
    ephir
    -0.06
     Manor
    -0.06
     Cabin
    -0.06
     sly
    -0.06
     unint
    -0.06
     Chun
    -0.06
    POSITIVE LOGITS
     Rose
    0.15
     rose
    0.12
    Rose
    0.12
    rose
    0.12
     Ros
    0.10
     ros
    0.10
    Ros
    0.10
    gos
    0.09
     ********
    0.09
     roses
    0.08
    Activations Density 0.010%

    No Known Activations