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. 92778
    Prev
    Next
    INDEX
    Explanations

    miscellaneous text

    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
    Upper
    -0.06
    _nd
    -0.06
    /apache
    -0.06
     lyn
    -0.06
     název
    -0.06
     Üst
    -0.06
     комнат
    -0.06
    人
    -0.06
     dél
    -0.06
    TestingModule
    -0.06
    POSITIVE LOGITS
    tah
    0.06
     linker
    0.06
     placements
    0.06
    iker
    0.06
    .Month
    0.06
    平台
    0.06
     ery
    0.06
     slices
    0.06
    _where
    0.06
    WebResponse
    0.06
    Activations Density 0.000%

    No Known Activations