© 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. 123918
    Prev
    Next
    INDEX
    Explanations

    code and technical answers

    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
    119
    -0.06
     Facility
    -0.06
     tuberculosis
    -0.06
     IDE
    -0.06
    GLOSS
    -0.06
     toplum
    -0.06
     modulus
    -0.06
    盒
    -0.06
    Alternative
    -0.06
    -svg
    -0.05
    POSITIVE LOGITS
    ไซ
    0.07
    くな
    0.07
     ):↵
    0.06
    啊啊
    0.06
    aye
    0.06
    ไป
    0.06
    uju
    0.06
     ауд
    0.06
    .Start
    0.06
     dared
    0.06
    Activations Density 0.084%

    No Known Activations