© 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. 7-RESID-POST-AA
    6. 30822
    Prev
    Next
    INDEX
    Explanations

    VSMC research

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disappe
    -0.07
     下跌
    -0.06
    єш
    -0.06
    UE
    -0.06
     الله
    -0.06
    (instr
    -0.06
     presenta
    -0.06
     blanco
    -0.06
    (include
    -0.06
     ".$
    -0.06
    POSITIVE LOGITS
     وص
    0.07
     ordinance
    0.06
    _terminal
    0.06
    ерина
    0.06
    (IService
    0.06
    scriptions
    0.06
    shi
    0.06
    -notification
    0.06
    simulation
    0.06
     ordinances
    0.06
    Activations Density 0.003%

    No Known Activations