Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87053
    Prev
    Next
    INDEX
    Explanations

    Lisp

    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
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    อากาศ
    -0.07
    	AT
    -0.07
    eatures
    -0.07
    NegativeButton
    -0.06
    fw
    -0.06
     fren
    -0.06
    ATAB
    -0.06
    Gal
    -0.06
     ẩm
    -0.06
     підготов
    -0.06
    POSITIVE LOGITS
     Lisp
    0.08
    isp
    0.07
    ISP
    0.07
     Russian
    0.07
    npm
    0.06
    .addProperty
    0.06
     иск
    0.06
     intermediary
    0.06
     fairly
    0.06
    Russian
    0.06
    Activations Density 0.001%

    No Known Activations