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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 45254
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     Aure
    -0.08
    sville
    -0.07
    Nr
    -0.07
     Lauren
    -0.06
    (selector
    -0.06
    ้าต
    -0.06
    "));
    -0.06
    вався
    -0.06
    egov
    -0.06
    ξι
    -0.06
    POSITIVE LOGITS
     filed
    0.07
    ig
    0.07
     gears
    0.06
    _flat
    0.06
    :test
    0.06
    /f
    0.06
    _thread
    0.06
     flats
    0.06
    ha
    0.06
    /apis
    0.06
    Activations Density 0.008%

    No Known Activations