© 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. 15-LLAMASCOPE-RES-131K
    11. 26745
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to equations or functions

    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
    ah
    -0.06
     Roth
    -0.06
     or
    -0.06
    less
    -0.06
    ama
    -0.06
     Jur
    -0.06
    dl
    -0.05
     Greatest
    -0.05
    ite
    -0.05
     ho
    -0.05
    POSITIVE LOGITS
    oš
    0.07
    okt
    0.07
    radient
    0.07
    .Callback
    0.07
    bjerg
    0.07
    anh
    0.07
    ãģŁãĤī
    0.07
    pis
    0.07
    edin
    0.07
    stants
    0.07
    Activations Density 0.001%

    No Known Activations