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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18987
    Prev
    Next
    INDEX
    Explanations

    options

    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
     kaps
    -0.06
     dela
    -0.06
     всю
    -0.06
     Lei
    -0.06
     cob
    -0.06
    aldo
    -0.06
     gö
    -0.06
     ст
    -0.06
     collisions
    -0.06
    Agregar
    -0.05
    POSITIVE LOGITS
     Ack
    0.07
    orthy
    0.07
    rin
    0.07
    ATHER
    0.07
    masının
    0.07
    >Total
    0.06
    Assertion
    0.06
    ライト
    0.06
     freshmen
    0.06
    overn
    0.06
    Activations Density 0.005%

    No Known Activations