© 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. 39386
    Prev
    Next
    INDEX
    Explanations

    musicians start young

    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
     biologist
    -0.07
    	expect
    -0.07
    _NORMAL
    -0.07
    	StringBuffer
    -0.07
    POSIT
    -0.07
    亿元
    -0.07
    _SIGNAL
    -0.07
    .VISIBLE
    -0.07
    .Resolve
    -0.06
    	Simple
    -0.06
    POSITIVE LOGITS
    awai
    0.08
     erre
    0.08
    ัด
    0.06
    쳐
    0.06
    /&
    0.06
    getOrElse
    0.06
    upyter
    0.06
     Garmin
    0.06
     поє
    0.06
     सप
    0.06
    Activations Density 0.013%

    No Known Activations