© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27-RESID-POST-AA
    11. 6691
    Prev
    Next
    INDEX
    Explanations

    University dorm life

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    330
    -0.07
     Protocol
    -0.07
    race
    -0.07
    -->↵
    -0.07
     طی
    -0.07
    人民共和国
    -0.07
     CPU
    -0.06
    LEVEL
    -0.06
    Interior
    -0.06
     boyunca
    -0.06
    POSITIVE LOGITS
     Jewel
    0.06
    <f
    0.06
    —is
    0.06
     fiery
    0.06
    bd
    0.06
    .divide
    0.05
    ughty
    0.05
    _MODULES
    0.05
    aseña
    0.05
     Čech
    0.05
    Activations Density 0.037%

    No Known Activations