Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 63572
    Prev
    Next
    INDEX
    Explanations

    Negative articles

    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
    ographers
    -0.06
    엔
    -0.06
    της
    -0.06
     др
    -0.06
    ходить
    -0.06
     ویژه
    -0.06
    ование
    -0.06
     destinations
    -0.06
     Advantage
    -0.06
     Fritz
    -0.06
    POSITIVE LOGITS
     employer
    0.06
     hate
    0.06
    emma
    0.06
    @author
    0.06
     onClick
    0.06
    .onClick
    0.06
     STEM
    0.06
     die
    0.06
     为
    0.06
     जन
    0.06
    Activations Density 0.019%

    No Known Activations