© 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. 13288
    Prev
    Next
    INDEX
    Explanations

    Code changes/deletion

    np_max-act · gemini-2.0-flash

    sentences or tokens that convey warnings, cautionary notes, or strong emphasis (danger/important notices).

    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
     peaked
    -0.07
     exchanged
    -0.07
     Oz
    -0.06
    たく
    -0.06
    WX
    -0.06
     DataTypes
    -0.06
    {return
    -0.06
    gd
    -0.06
     Eclipse
    -0.06
     brains
    -0.06
    POSITIVE LOGITS
    .confirm
    0.07
     können
    0.06
    ्शन
    0.06
     müssen
    0.06
    410
    0.06
     регі
    0.06
    .Disclaimer
    0.06
    (import
    0.06
    ністю
    0.06
     ming
    0.06
    Activations Density 0.158%

    No Known Activations