© 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. 29075
    Prev
    Next
    INDEX
    Explanations

    programming construct comparisons, specifically checking for equality

    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
    amp
    -0.07
    ial
    -0.07
    roz
    -0.07
    ãĤ¥
    -0.06
    aday
    -0.06
    Neal
    -0.06
    ialized
    -0.06
    izm
    -0.06
    cw
    -0.06
    straints
    -0.06
    POSITIVE LOGITS
    avage
    0.07
    nar
    0.06
    ignet
    0.06
    asse
    0.06
    ologne
    0.06
    322
    0.06
    auer
    0.06
    /dis
    0.06
    /not
    0.06
    .OrderBy
    0.06
    Activations Density 0.006%

    No Known Activations