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. 87030
    Prev
    Next
    INDEX
    Explanations

    studies

    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
     enerji
    -0.07
     взаєм
    -0.06
     rail
    -0.06
     ApplicationException
    -0.06
    rowsable
    -0.06
     conductor
    -0.06
    iciel
    -0.05
     faux
    -0.05
     ani
    -0.05
    occasion
    -0.05
    POSITIVE LOGITS
     więc
    0.07
    .loading
    0.07
     hed
    0.07
    leading
    0.06
     History
    0.06
    UNCTION
    0.06
    olders
    0.06
    åde
    0.06
    .requires
    0.06
    module
    0.06
    Activations Density 0.032%

    No Known Activations