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. 87075
    Prev
    Next
    INDEX
    Explanations

    or

    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
    olio
    -0.07
    Saved
    -0.07
    ��
    -0.07
     trailers
    -0.07
    회
    -0.06
    timer
    -0.06
     plants
    -0.06
     universally
    -0.06
    FAQ
    -0.06
    ानद
    -0.06
    POSITIVE LOGITS
     stdin
    0.07
     dracon
    0.07
     NEC
    0.06
    드로
    0.06
     Tüm
    0.06
     sns
    0.06
     Aut
    0.06
    rovers
    0.06
    teness
    0.06
    ({
    ↵
    0.06
    Activations Density 0.020%

    No Known Activations