© 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. 11-RESID-POST-AA
    6. 19981
    Prev
    Next
    INDEX
    Explanations

    anesthesia

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ปฏ
    -0.07
    dish
    -0.07
    Capture
    -0.06
    .jar
    -0.06
    Fair
    -0.06
    ポ
    -0.06
    Creators
    -0.06
    NumberOf
    -0.06
    (TimeSpan
    -0.06
    “My
    -0.06
    POSITIVE LOGITS
     náklad
    0.06
    _mov
    0.06
    .BackgroundImage
    0.06
     modne
    0.06
     attitudes
    0.06
    ød
    0.06
     соедин
    0.06
    ่าวว
    0.06
     STL
    0.06
     lesbisk
    0.06
    Activations Density 0.002%

    No Known Activations