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. 87033
    Prev
    Next
    INDEX
    Explanations

    colons

    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
    goog
    -0.07
     вам
    -0.07
    addons
    -0.07
     abych
    -0.06
    ematik
    -0.06
    öyle
    -0.06
     yapılacak
    -0.06
     og
    -0.06
    liğine
    -0.06
    .are
    -0.06
    POSITIVE LOGITS
    _shadow
    0.07
    =========↵
    0.07
    acker
    0.06
     critiques
    0.06
    prime
    0.06
    -inter
    0.06
    waves
    0.06
    	event
    0.06
    AuthToken
    0.06
    leading
    0.06
    Activations Density 0.010%

    No Known Activations