© 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 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. 103504
    Prev
    Next
    INDEX
    Explanations

    numbered items or steps

    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
    『
    -0.07
    uyla
    -0.06
    info
    -0.06
    ments
    -0.06
    itter
    -0.06
    .writeHead
    -0.06
    それは
    -0.06
    ribly
    -0.06
    @return
    -0.06
     biç
    -0.06
    POSITIVE LOGITS
     Ramsey
    0.07
     Conrad
    0.07
    fn
    0.06
     consequently
    0.06
     stata
    0.06
     Banc
    0.06
     أفضل
    0.06
     RAND
    0.06
    strip
    0.06
     вра
    0.06
    Activations Density 0.076%

    No Known Activations