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. 87049
    Prev
    Next
    INDEX
    Explanations

    founding organizations

    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
     sequence
    -0.07
     Lime
    -0.07
    _busy
    -0.07
     бо
    -0.07
    oded
    -0.07
     Shrine
    -0.07
     lover
    -0.06
     delay
    -0.06
    иг
    -0.06
    224
    -0.06
    POSITIVE LOGITS
     formed
    0.08
     established
    0.07
     secretion
    0.07
     kö
    0.07
     creates
    0.07
     creation
    0.07
     Ptr
    0.07
     created
    0.06
     funcion
    0.06
     bran
    0.06
    Activations Density 0.048%

    No Known Activations