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. 87046
    Prev
    Next
    INDEX
    Explanations

    <

    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
     Jenkins
    -0.07
    asons
    -0.07
    qed
    -0.07
    Authority
    -0.07
     setDate
    -0.07
    ERA
    -0.07
    AILABLE
    -0.06
     algum
    -0.06
     dando
    -0.06
    ERAL
    -0.06
    POSITIVE LOGITS
     mitig
    0.06
    闘
    0.06
     drifted
    0.06
     처리
    0.06
     उत
    0.06
    <div
    0.06
    dotenv
    0.06
    jualan
    0.06
    Під
    0.06
     �
    0.06
    Activations Density 0.000%

    No Known Activations