© 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. 88496
    Prev
    Next
    INDEX
    Explanations

    links and references to online resources

    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
    errat
    -0.08
    laden
    -0.07
    inand
    -0.07
    reater
    -0.07
    elin
    -0.07
     Trap
    -0.06
    inox
    -0.06
    ahat
    -0.06
    unting
    -0.06
    pData
    -0.06
    POSITIVE LOGITS
    oodle
    0.06
    ymes
    0.06
    ode
    0.06
     showAlert
    0.06
     NDEBUG
    0.06
    verb
    0.06
     Celt
    0.06
    iative
    0.05
    _fr
    0.05
    umer
    0.05
    Activations Density 0.003%

    No Known Activations