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. 87020
    Prev
    Next
    INDEX
    Explanations

    Medical research

    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
    ....↵
    -0.07
    	device
    -0.07
    =post
    -0.07
     userID
    -0.07
     اینترنتی
    -0.07
    .tf
    -0.07
    _km
    -0.06
    +","+
    -0.06
     Employee
    -0.06
     سایت
    -0.06
    POSITIVE LOGITS
    vpn
    0.07
    -->
    ↵
    0.06
    .randn
    0.06
    льт
    0.06
    odoxy
    0.06
     될
    0.06
     이런
    0.06
    زية
    0.06
    зн
    0.06
    प
    0.06
    Activations Density 0.151%

    No Known Activations