© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 1633
    Prev
    Next
    INDEX
    Explanations

    prepositions/articles

    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
    agn
    -0.07
     sq
    -0.07
    894
    -0.07
    ์อ
    -0.06
    runtime
    -0.06
     brutal
    -0.06
     Tours
    -0.06
    ugar
    -0.06
     graphics
    -0.06
    .customer
    -0.06
    POSITIVE LOGITS
     spear
    0.07
     상담
    0.06
     Buyer
    0.06
    .preventDefault
    0.06
    _statistics
    0.06
    .appendChild
    0.06
     coherence
    0.06
     FLAC
    0.06
     acknowled
    0.06
     článek
    0.06
    Activations Density 0.021%

    No Known Activations