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. 15-RESID-POST-AA
    6. 15382
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
     اضافه
    -0.07
    umnos
    -0.07
     requestBody
    -0.07
     Pride
    -0.06
    (Employee
    -0.06
    _NO
    -0.06
    ikon
    -0.06
     Enh
    -0.06
     inform
    -0.06
     配
    -0.06
    POSITIVE LOGITS
    ()));
    0.08
     MetroFramework
    0.07
     Dick
    0.07
     burgeoning
    0.07
     Deng
    0.07
    ,...
    0.07
    }})↵
    0.06
    '])){
    0.06
    	port
    0.06
    ))]
    0.06
    Activations Density 0.190%

    No Known Activations