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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 99877
    Prev
    Next
    INDEX
    Explanations

    you

    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
    ежать
    -0.07
    وره
    -0.07
    杀
    -0.06
    Cos
    -0.06
    نوع
    -0.06
    Get
    -0.06
     bureaucrats
    -0.06
    дут
    -0.06
    issors
    -0.06
    _Att
    -0.06
    POSITIVE LOGITS
    +=(
    0.07
    =#{
    0.07
    قد
    0.07
     nev
    0.06
    ]=[
    0.06
    >N
    0.06
     (*)(
    0.06
    .getRequest
    0.06
     IIC
    0.06
     Aj
    0.06
    Activations Density 0.052%

    No Known Activations