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

    Neuronpedia

    APICircuit 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. 111276
    Prev
    Next
    INDEX
    Explanations

    straightforward

    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
     selection
    -0.07
    Selection
    -0.06
    ,&
    -0.06
     kul
    -0.06
     agli
    -0.06
     Năm
    -0.06
    ei
    -0.06
    held
    -0.06
     selected
    -0.06
    osomal
    -0.06
    POSITIVE LOGITS
     straightforward
    0.08
     Broad
    0.07
    .А
    0.07
    렵
    0.07
    maktadır
    0.07
     whispers
    0.06
     moh
    0.06
    .Prot
    0.06
     LA
    0.06
    РА
    0.06
    Activations Density 0.002%

    No Known Activations