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. 15-RESID-POST-AA
    6. 10989
    Prev
    Next
    INDEX
    Explanations

    .org

    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
     hlavu
    -0.06
     مشار
    -0.06
    ूछ
    -0.06
    dotenv
    -0.06
    顾
    -0.06
     quay
    -0.06
     taş
    -0.06
     QU
    -0.06
    .TextBox
    -0.06
    stra
    -0.06
    POSITIVE LOGITS
    olet
    0.07
    nde
    0.06
    FC
    0.06
     христи
    0.06
    ee
    0.06
    ческое
    0.06
    нє
    0.06
    yum
    0.06
    vasive
    0.06
    oler
    0.06
    Activations Density 0.006%

    No Known Activations