© 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. 19-RESID-POST-AA
    6. 86821
    Prev
    Next
    INDEX
    Explanations

    based

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pollen
    -0.07
    ection
    -0.06
     我
    -0.06
    	dist
    -0.06
    llum
    -0.06
     forme
    -0.06
    we
    -0.06
    _chat
    -0.06
    	Double
    -0.06
     ));
    -0.06
    POSITIVE LOGITS
    _sun
    0.07
    osoph
    0.07
     based
    0.07
     unseen
    0.06
     попада
    0.06
    >',↵
    0.06
    _TE
    0.06
     kiểu
    0.06
    /em
    0.06
    】↵↵
    0.06
    Activations Density 0.025%

    No Known Activations