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. 87028
    Prev
    Next
    INDEX
    Explanations

    deep

    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
     inhibitors
    -0.07
    elts
    -0.07
     eines
    -0.07
    Hat
    -0.07
    reation
    -0.07
    mada
    -0.06
    ма
    -0.06
    WX
    -0.06
    modity
    -0.06
    interpreter
    -0.06
    POSITIVE LOGITS
     DONE
    0.07
    circ
    0.06
    -redux
    0.06
    مدة
    0.06
     mistake
    0.06
     conducted
    0.06
    __
    0.06
     RectTransform
    0.06
    ->__
    0.06
    _U
    0.06
    Activations Density 0.002%

    No Known Activations