© 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. 9-LLAMASCOPE-RES-131K
    11. 96252
    Prev
    Next
    INDEX
    Explanations

    references to the quantity of items or associated groups 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
    ADED
    -0.07
    reau
    -0.07
    ernet
    -0.06
    edia
    -0.06
    reck
    -0.06
    information
    -0.06
     Ming
    -0.06
    ifer
    -0.06
    ampler
    -0.06
    gin
    -0.06
    POSITIVE LOGITS
    asje
    0.07
    _globals
    0.07
    Calibri
    0.07
    itura
    0.07
     alike
    0.06
    ollywood
    0.06
     -*-č↵
    0.06
    ýt
    0.06
    htar
    0.06
     Tul
    0.06
    Activations Density 0.007%

    No Known Activations