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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 77695
    Prev
    Next
    INDEX
    Explanations

    let

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     рабо
    -0.07
     analý
    -0.07
     ノ
    -0.06
     похож
    -0.06
    جاد
    -0.06
    _/
    -0.06
    getImage
    -0.06
    mare
    -0.06
     naš
    -0.06
    š
    -0.06
    POSITIVE LOGITS
     formatted
    0.07
    PO
    0.07
     LJ
    0.07
     RR
    0.07
     separate
    0.07
     Let
    0.07
     Opp
    0.06
     /*!↵
    0.06
     Tep
    0.06
    ======↵
    0.06
    Activations Density 0.015%

    No Known Activations