© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 37256
    Prev
    Next
    INDEX
    Explanations

    Wagner and Portsmouth

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     등을
    -0.07
    ">%
    -0.07
     toward
    -0.07
    感到
    -0.07
     estimate
    -0.07
    favorites
    -0.07
     ARRAY
    -0.07
     exposures
    -0.07
    /********
    -0.07
     어떻게
    -0.07
    POSITIVE LOGITS
    asha
    0.07
    isky
    0.07
    [DllImport
    0.07
     headers
    0.06
    _charset
    0.06
     Employ
    0.06
     sdl
    0.06
    aines
    0.06
     Gib
    0.06
    ahun
    0.06
    Activations Density 0.109%

    No Known Activations