© 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. 19-RESID-POST-AA
    6. 117991
    Prev
    Next
    INDEX
    Explanations

    KDE

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alignment
    -0.07
     Hust
    -0.07
    -owned
    -0.07
    Radio
    -0.07
    (Me
    -0.07
     Regents
    -0.07
    普
    -0.07
     sheets
    -0.06
     antibodies
    -0.06
    ाथ
    -0.06
    POSITIVE LOGITS
     disin
    0.06
     Ngb
    0.06
    cono
    0.06
    classname
    0.06
     tabBar
    0.06
    させ
    0.06
     melod
    0.05
     LGBT
    0.05
     출
    0.05
     Gibbs
    0.05
    Activations Density 0.009%

    No Known Activations