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. 112850
    Prev
    Next
    INDEX
    Explanations

    Religious quotes

    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
    umberland
    -0.07
    Surv
    -0.07
    จำนวน
    -0.07
     опыт
    -0.06
    nds
    -0.06
    ndl
    -0.06
    RITE
    -0.06
    illaume
    -0.06
    /gallery
    -0.06
    ascular
    -0.06
    POSITIVE LOGITS
     bowls
    0.07
    atır
    0.06
    _Log
    0.06
     advancements
    0.06
    -Speed
    0.06
    _PIXEL
    0.06
    _forms
    0.06
    toFloat
    0.06
    алів
    0.06
    `;↵↵
    0.06
    Activations Density 0.000%

    No Known Activations