© 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
    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. 106887
    Prev
    Next
    INDEX
    Explanations

    Malicious detection

    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
    Parse
    -0.07
    time
    -0.06
    _);↵
    -0.06
     Jude
    -0.06
    >.
    -0.06
     medals
    -0.06
     JP
    -0.06
    Touches
    -0.06
    empty
    -0.06
     JC
    -0.06
    POSITIVE LOGITS
    нее
    0.06
     spiral
    0.06
     число
    0.06
     податков
    0.06
    =db
    0.06
    AMESPACE
    0.06
    .Anchor
    0.06
     cord
    0.06
    .makedirs
    0.06
    лась
    0.06
    Activations Density 0.048%

    No Known Activations