© 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. 15-RESID-POST-AA
    11. 127764
    Prev
    Next
    INDEX
    Explanations

    Code or technical language

    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
     cant
    -0.06
     كار
    -0.06
     รอง
    -0.06
     Floral
    -0.06
     thủy
    -0.06
     Franken
    -0.06
     fiat
    -0.06
     kazanç
    -0.05
     corres
    -0.05
    朱
    -0.05
    POSITIVE LOGITS
    -source
    0.07
    -з
    0.07
     freaking
    0.06
    Med
    0.06
     disposing
    0.06
    ETERS
    0.06
     stalo
    0.06
    arian
    0.06
    arking
    0.06
    policy
    0.06
    Activations Density 0.000%

    No Known Activations