© 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. 15-RESID-POST-AA
    6. 55807
    Prev
    Next
    INDEX
    Explanations

    offering services

    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
    湖
    -0.07
    机械
    -0.07
    اع
    -0.07
     ヾ
    -0.07
    based
    -0.06
    edores
    -0.06
    哦
    -0.06
    NSError
    -0.06
     mills
    -0.06
    地
    -0.06
    POSITIVE LOGITS
    zení
    0.07
     سمت
    0.06
     Retorna
    0.06
    (front
    0.06
    (false
    0.06
    Allocation
    0.06
     formul
    0.06
    respuesta
    0.06
     payloads
    0.06
    	system
    0.06
    Activations Density 0.149%

    No Known Activations