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. 27680
    Prev
    Next
    INDEX
    Explanations

    industry and related services

    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
     Этот
    -0.07
     doing
    -0.07
     Eggs
    -0.07
    Catalog
    -0.06
     Jill
    -0.06
     Diameter
    -0.06
    	true
    -0.06
     zoals
    -0.06
    ۱۵
    -0.06
     вмі
    -0.06
    POSITIVE LOGITS
     slip
    0.08
    eryl
    0.07
     DateTimeOffset
    0.07
    ंटर
    0.06
     perpetrated
    0.06
    чив
    0.06
    ?>
    ↵
    0.06
    основ
    0.06
     Louisville
    0.06
     نم
    0.06
    Activations Density 0.072%

    No Known Activations