© 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 EvalsExportsinterp-engineNEWAPI 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. 87213
    Prev
    Next
    INDEX
    Explanations

    Code headers

    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
     Implicit
    -0.07
     Chỉ
    -0.07
     bullish
    -0.06
    Implicit
    -0.06
     implicit
    -0.06
     ASSIGN
    -0.06
    _fault
    -0.06
    Attributes
    -0.06
    press
    -0.06
    Updated
    -0.06
    POSITIVE LOGITS
    函
    0.07
    مم
    0.07
    .vocab
    0.07
    ------
    0.06
     unitOfWork
    0.06
    すれば
    0.06
    ，”
    0.06
     dla
    0.06
     메
    0.06
    neo
    0.06
    Activations Density 0.003%

    No Known Activations