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. 7-RESID-POST-AA
    6. 99715
    Prev
    Next
    INDEX
    Explanations

    programming files

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    êm
    -0.07
     '/../
    -0.06
     제작
    -0.06
    _FLAG
    -0.06
     arasındaki
    -0.06
     om
    -0.06
    .Replace
    -0.06
    bras
    -0.06
     cél
    -0.06
    /init
    -0.06
    POSITIVE LOGITS
    .dylib
    0.07
     Greens
    0.06
    ypi
    0.06
     ymin
    0.06
    还是
    0.06
    伙
    0.06
    过程
    0.06
    :UIControl
    0.06
    дая
    0.06
    �
    0.06
    Activations Density 0.001%

    No Known Activations