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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 101988
    Prev
    Next
    INDEX
    Explanations

    reviews and evaluations

    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
    _ped
    -0.07
    -sn
    -0.07
     жов
    -0.06
         	
    -0.06
     editorial
    -0.06
    Inserted
    -0.06
    Bg
    -0.06
    {/*
    -0.06
     فال
    -0.06
     Lau
    -0.06
    POSITIVE LOGITS
    rix
    0.07
     Kubernetes
    0.06
    "].
    0.06
    ych
    0.06
     abandonment
    0.06
     Disorders
    0.06
     bikini
    0.06
     WELL
    0.06
     bilingual
    0.06
    RIX
    0.06
    Activations Density 0.158%

    No Known Activations