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. 87067
    Prev
    Next
    INDEX
    Explanations

    question and answer

    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
    register
    -0.07
    モン
    -0.07
    ОВ
    -0.06
     openness
    -0.06
    经理
    -0.06
    ~↵↵
    -0.06
     persists
    -0.06
     intens
    -0.06
    #'
    -0.06
    .)↵
    -0.06
    POSITIVE LOGITS
    cstring
    0.07
     awaiting
    0.06
     Fence
    0.06
     Tomas
    0.06
     vibrations
    0.06
    \App
    0.06
    (sess
    0.06
    _buffers
    0.06
     aider
    0.06
    仪
    0.06
    Activations Density 0.039%

    No Known Activations