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. 19-RESID-POST-AA
    6. 27520
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     riots
    -0.07
     imprimir
    -0.07
     Stopwatch
    -0.06
     xu
    -0.06
     tall
    -0.06
     ду
    -0.06
    _star
    -0.06
    ım
    -0.06
     بالاتر
    -0.06
    ".↵
    -0.06
    POSITIVE LOGITS
    TextChanged
    0.07
     khám
    0.07
    .Ref
    0.06
     Kendrick
    0.06
     KeyValue
    0.06
    MemoryWarning
    0.06
    .SubItems
    0.06
    employ
    0.06
     контролю
    0.06
    .more
    0.06
    Activations Density 0.004%

    No Known Activations