© 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. 11-RESID-POST-AA
    11. 76776
    Prev
    Next
    INDEX
    Explanations

    plot descriptions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mexican
    -0.08
     form
    -0.06
     Loren
    -0.06
    폰
    -0.06
     admission
    -0.06
    _un
    -0.06
     largest
    -0.06
    ificados
    -0.06
     Buk
    -0.06
     hud
    -0.06
    POSITIVE LOGITS
    liğinde
    0.07
     teng
    0.07
    _Email
    0.07
    _string
    0.06
     příro
    0.06
    skou
    0.06
    dál
    0.06
    xbc
    0.06
     sab
    0.06
     folly
    0.06
    Activations Density 0.025%

    No Known Activations