© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 77303
    Prev
    Next
    INDEX
    Explanations

    security vulnerabilities

    np_max-act · gemini-2.0-flash

    statements about cybersecurity and privacy risks, especially vulnerabilities that expose sensitive information or credentials and enable attacks.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shelby
    -0.07
    ITTER
    -0.06
    tes
    -0.06
     шт
    -0.06
     eigentlich
    -0.06
     المت
    -0.06
    et
    -0.06
    €€
    -0.06
    故
    -0.06
     fireplace
    -0.06
    POSITIVE LOGITS
     него
    0.07
    Ron
    0.07
    某
    0.06
    monthly
    0.06
     campaigning
    0.06
    .An
    0.06
    สง
    0.06
     dao
    0.06
     impoverished
    0.06
    Holy
    0.06
    Activations Density 0.244%

    No Known Activations