Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-RESID-POST-AA
    6. 83508
    Prev
    Next
    INDEX
    Explanations

    code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    答案
    -0.06
     круг
    -0.06
     παρα
    -0.06
     类
    -0.06
    llvm
    -0.06
     Eine
    -0.06
     网
    -0.06
    (Label
    -0.06
    衡
    -0.06
     '{}
    -0.06
    POSITIVE LOGITS
    ollectors
    0.07
     Extr
    0.07
     PTR
    0.07
     Functional
    0.06
    NK
    0.06
     functional
    0.06
    喔
    0.06
    _training
    0.06
    ticket
    0.06
     mileage
    0.06
    Activations Density 0.011%

    No Known Activations