© 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. 15-RESID-POST-AA
    11. 6254
    Prev
    Next
    INDEX
    Explanations

    spin

    np_max-act · gemini-2.0-flash

    the neuron detects spin-lock and related kernel synchronization identifiers (e.g., "spin_lock_t", "spin", "lock").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    TEGR
    -0.07
     escol
    -0.07
     Algebra
    -0.06
     Urb
    -0.06
     Baker
    -0.06
    _review
    -0.06
     genome
    -0.06
     Paolo
    -0.06
    lbrakk
    -0.06
     characterization
    -0.06
    POSITIVE LOGITS
    venir
    0.07
    爸
    0.06
    bufio
    0.06
    plier
    0.06
    _weak
    0.06
    .HashMap
    0.06
    _css
    0.06
    roi
    0.06
    重要
    0.06
    Chooser
    0.06
    Activations Density 0.002%

    No Known Activations