© 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. 88661
    Prev
    Next
    INDEX
    Explanations

    terms related to innovation and improvement in various contexts

    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
    pty
    -0.07
     ван
    -0.06
    elon
    -0.06
     Byl
    -0.06
    atif
    -0.06
    uguay
    -0.06
    llib
    -0.06
    emark
    -0.06
    lrt
    -0.06
    uze
    -0.06
    POSITIVE LOGITS
     inval
    0.06
    æĢ§èĥ½
    0.06
    /cop
    0.06
     architekt
    0.06
     cá
    0.06
     civilian
    0.06
     publicly
    0.06
    _gettime
    0.06
    oloji
    0.05
    empo
    0.05
    Activations Density 0.047%

    No Known Activations