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. 15-RESID-POST-AA
    6. 110744
    Prev
    Next
    INDEX
    Explanations

    obesity and health risks

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    路径
    -0.06
     tặng
    -0.06
     stereotype
    -0.06
     Gate
    -0.06
    uir
    -0.06
    kul
    -0.06
    Outline
    -0.06
     selfie
    -0.06
    .encrypt
    -0.06
    `\
    -0.06
    POSITIVE LOGITS
     wit
    0.07
    стер
    0.07
     där
    0.07
     Мин
    0.06
    _CRE
    0.06
    dds
    0.06
    uppies
    0.06
    été
    0.06
    LEGAL
    0.06
     Nutzung
    0.06
    Activations Density 0.106%

    No Known Activations