© 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. 75252
    Prev
    Next
    INDEX
    Explanations

    training

    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
    The
    -0.07
    ,the
    -0.06
    Directions
    -0.06
    rung
    -0.06
    systems
    -0.06
    اجر
    -0.06
     irrational
    -0.06
     rewarded
    -0.06
    ований
    -0.06
    ньої
    -0.06
    POSITIVE LOGITS
    _main
    0.06
    (group
    0.06
     있을
    0.06
    _EVAL
    0.06
    ς
    0.06
     QMainWindow
    0.06
    @dynamic
    0.06
    _ph
    0.06
    (null
    0.06
    .Apply
    0.05
    Activations Density 0.108%

    No Known Activations