© 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. 119719
    Prev
    Next
    INDEX
    Explanations

    unusual genetic references related to soybeans

    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
    gi
    -0.07
     and
    -0.06
    fol
    -0.06
    ç
    -0.06
     synaptic
    -0.06
     sire
    -0.06
    åĩ¡
    -0.06
    xn
    -0.06
     which
    -0.06
     &
    -0.06
    POSITIVE LOGITS
    mouseup
    0.07
    aroo
    0.07
    .Guna
    0.07
    aukee
    0.07
    aldi
    0.07
    elda
    0.07
    atrix
    0.07
    allon
    0.06
    _PTR
    0.06
    .Bunifu
    0.06
    Activations Density 0.001%

    No Known Activations