© 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. 92061
    Prev
    Next
    INDEX
    Explanations

    Movie cast lists

    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
    clusive
    -0.07
    วาง
    -0.06
     Dak
    -0.06
    .$
    -0.06
    _uc
    -0.06
     Boyd
    -0.06
     vole
    -0.06
     Boots
    -0.06
     suicidal
    -0.06
     Quyết
    -0.06
    POSITIVE LOGITS
    �
    0.06
     ميل
    0.06
     WEB
    0.06
     Casual
    0.06
     Punk
    0.06
     StartCoroutine
    0.06
     relentlessly
    0.06
     Кам
    0.06
     udrž
    0.06
     声
    0.06
    Activations Density 0.004%

    No Known Activations