© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 54822
    Prev
    Next
    INDEX
    Explanations

    paused

    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
    fleet
    -0.06
    -three
    -0.06
     деятель
    -0.06
    bearer
    -0.06
    First
    -0.06
    rq
    -0.06
    headed
    -0.05
    RowAnimation
    -0.05
     resentment
    -0.05
    antas
    -0.05
    POSITIVE LOGITS
    ائج
    0.07
    _Run
    0.06
    ?>↵↵↵
    0.06
    _CODES
    0.06
    meta
    0.06
    葡
    0.06
    (egt
    0.06
    _um
    0.06
     及
    0.06
     dokonce
    0.06
    Activations Density 0.002%

    No Known Activations