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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 43366
    Prev
    Next
    INDEX
    Explanations

    You

    np_max-act · gemini-2.0-flash

    It detects in-game system messages or player-directed notifications, especially lines beginning with "You" or quoted status messages.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    .jpeg
    -0.07
    .png
    -0.06
    董
    -0.06
     Blu
    -0.06
    _softmax
    -0.06
    -0.06
    _CD
    -0.06
     dicho
    -0.06
     rừng
    -0.06
     Hernandez
    -0.06
    POSITIVE LOGITS
    feb
    0.06
    getRow
    0.06
    ổi
    0.06
    (cp
    0.06
    ýval
    0.06
     snapping
    0.06
    udging
    0.06
    ائلة
    0.06
    .palette
    0.06
    .GetSize
    0.06
    Activations Density 0.154%

    No Known Activations