© 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 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. 27-RESID-POST-AA
    11. 11330
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _PROPERTIES
    -0.08
    //================================================
    -0.07
    upakan
    -0.07
     Ngoài
    -0.07
     удив
    -0.07
     swung
    -0.07
     vertical
    -0.06
     lieu
    -0.06
    下去
    -0.06
    atum
    -0.06
    POSITIVE LOGITS
     알
    0.07
     Capability
    0.06
     حافظ
    0.06
     cyclist
    0.06
    ToFront
    0.06
    <|begin_of_text|>
    0.06
    =";↵
    0.06
     nejd
    0.06
     oprav
    0.06
     Tottenham
    0.06
    Activations Density 0.002%

    No Known Activations