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

    Neuronpedia

    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. 129517
    Prev
    Next
    INDEX
    Explanations

    terms related to viral infections and their cellular interactions

    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
    stal
    -0.06
    ADI
    -0.06
    ults
    -0.06
    isposable
    -0.06
    loub
    -0.06
     è´
    -0.06
    ãĤ·ãĤ§
    -0.06
     ÅĻ
    -0.06
    efon
    -0.06
     scl
    -0.06
    POSITIVE LOGITS
    anj
    0.07
    azine
    0.06
     experiment
    0.06
    anja
    0.06
    unpack
    0.06
    Seleccione
    0.06
    ystack
    0.06
    geom
    0.06
     whereas
    0.06
    agram
    0.06
    Activations Density 0.062%

    No Known Activations