© 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. 29923
    Prev
    Next
    INDEX
    Explanations

    the term "virtually" or related concepts indicating a degree of approximation or resemblance

    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
    ed
    -0.08
    ersen
    -0.08
    iola
    -0.07
    irsch
    -0.06
    æĮĩæķ°
    -0.06
    282
    -0.06
    294
    -0.06
    eur
    -0.06
    -fashioned
    -0.06
    erville
    -0.06
    POSITIVE LOGITS
    mente
    0.09
    lland
    0.07
    wner
    0.07
     entire
    0.07
    istically
    0.07
     Vest
    0.07
     же
    0.07
     impossible
    0.07
    ighted
    0.06
    heed
    0.06
    Activations Density 0.007%

    No Known Activations