© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55603
    Prev
    Next
    INDEX
    Explanations

    symbols and variables related to mathematical equations in scientific 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
     asympt
    -0.06
     Cher
    -0.06
    rias
    -0.06
     lore
    -0.05
     Rap
    -0.05
     fore
    -0.05
    IOC
    -0.05
     bars
    -0.05
     Biz
    -0.05
    inue
    -0.05
    POSITIVE LOGITS
    $MESS
    0.08
    batim
    0.08
    icut
    0.07
     osp
    0.07
    _critical
    0.07
    gra
    0.07
     Critical
    0.07
    agraph
    0.07
    rene
    0.06
    ØŃÙħ
    0.06
    Activations Density 0.228%

    No Known Activations