© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128779
    Prev
    Next
    INDEX
    Explanations

    Code/configuration files

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially attribute values) in structured markup or config files (e.g. numbers in XML attributes or JSON fields).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solic
    -0.07
     еди
    -0.06
    ู่
    -0.06
     fermentation
    -0.06
    adena
    -0.06
    дем
    -0.06
    (:,:,
    -0.06
    หนอง
    -0.06
     đen
    -0.06
    -S
    -0.06
    POSITIVE LOGITS
    .work
    0.07
     Birch
    0.07
    _touch
    0.06
    fetch
    0.06
     ioctl
    0.06
    623
    0.06
     setUp
    0.06
    _FILENO
    0.06
    .toggle
    0.06
    .FileReader
    0.06
    Activations Density 0.003%

    No Known Activations