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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 27-RESID-POST-AA
    6. 9750
    Prev
    Next
    INDEX
    Explanations

    door

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kanı
    -0.07
     proble
    -0.07
    antes
    -0.06
    '),
    -0.06
     convened
    -0.06
     Lines
    -0.06
     getProperty
    -0.06
     enfants
    -0.06
    Urls
    -0.06
     чуд
    -0.06
    POSITIVE LOGITS
    goals
    0.07
     juxtap
    0.06
     เล
    0.06
    uelle
    0.06
    .sprite
    0.06
    Crystal
    0.06
    privileged
    0.06
     Бел
    0.06
    ीं
    0.06
    _scene
    0.06
    Activations Density 0.022%

    No Known Activations