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

    Neuronpedia

    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. 19644
    Prev
    Next
    INDEX
    Explanations

    Use it or lose it

    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
     undesirable
    -0.07
    新增
    -0.06
    gem
    -0.06
    )did
    -0.06
    ohen
    -0.06
    .toggle
    -0.06
    lk
    -0.06
     Cohen
    -0.06
    _war
    -0.06
    /lib
    -0.06
    POSITIVE LOGITS
     thrown
    0.07
    Yep
    0.07
     пользователя
    0.06
     أنه
    0.06
    ového
    0.06
    Preferred
    0.06
     Bits
    0.06
    Reject
    0.06
     too
    0.06
     vàng
    0.06
    Activations Density 0.178%

    No Known Activations