© 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. 93820
    Prev
    Next
    INDEX
    Explanations

    elements related to specific details or classifications

    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
    ová
    -0.07
    ckett
    -0.07
    cov
    -0.07
    alla
    -0.07
    ddit
    -0.07
    orus
    -0.07
    umph
    -0.07
    /lg
    -0.07
    TickCount
    -0.07
    ỡ
    -0.07
    POSITIVE LOGITS
     according
    0.07
    리ìĸ´
    0.07
    242
    0.06
    isse
    0.06
    ras
    0.06
    heim
    0.06
    -Sah
    0.06
    cen
    0.06
    842
    0.06
    yme
    0.06
    Activations Density 0.001%

    No Known Activations