© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57307
    Prev
    Next
    INDEX
    Explanations

    references to data structure comparisons and order in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndView
    -0.07
    usize
    -0.07
    atinum
    -0.07
     Radius
    -0.07
    ÏĦÏģι
    -0.07
    eses
    -0.06
    ç¹ģ
    -0.06
    ovky
    -0.06
    ãĥ¼ãĥ©
    -0.06
    quate
    -0.06
    POSITIVE LOGITS
     order
    0.11
    _order
    0.09
     Order
    0.09
     ORDER
    0.08
    Order
    0.08
    -order
    0.07
    order
    0.07
    ORDER
    0.07
    _ORDER
    0.07
     ordering
    0.07
    Activations Density 0.010%

    No Known Activations