© 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. 128133
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and state-of-the-art achievements in machine learning models

    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
    lassen
    -0.06
     Lob
    -0.06
    oble
    -0.06
     Neb
    -0.06
    olle
    -0.06
    ado
    -0.06
    ew
    -0.05
    ayo
    -0.05
    amo
    -0.05
    âĢ¦↵
    -0.05
    POSITIVE LOGITS
    /current
    0.08
    даÑĤ
    0.08
    CallCheck
    0.08
    DOMNode
    0.08
    odash
    0.08
    ÐķС
    0.08
    CppClass
    0.07
    夫人
    0.07
    alars
    0.07
    rowable
    0.07
    Activations Density 0.007%

    No Known Activations