© 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. 82890
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with statistical data or metrics

    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
    cle
    -0.06
    Servlet
    -0.06
    asu
    -0.05
    alon
    -0.05
    onym
    -0.05
    身ä¸Ĭ
    -0.05
    \Bundle
    -0.05
     ref
    -0.05
    лев
    -0.05
    iam
    -0.05
    POSITIVE LOGITS
    pollo
    0.08
    riba
    0.08
    ovsky
    0.08
    rlen
    0.07
    çĦ¡ãģĹãģ
    0.07
     (*((
    0.07
    wner
    0.07
    /-
    0.07
    achten
    0.07
    ystore
    0.07
    Activations Density 0.038%

    No Known Activations