© 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. 75052
    Prev
    Next
    INDEX
    Explanations

    mentions of achievements and milestones in sports

    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
    rias
    -0.06
    gart
    -0.06
    atic
    -0.06
     Cir
    -0.06
     vanity
    -0.06
     cir
    -0.06
    ÏĨο
    -0.06
    ehen
    -0.06
    _formula
    -0.06
    ãĥªãĤ¢
    -0.06
    POSITIVE LOGITS
     gender
    0.09
    Women
    0.08
     Gender
    0.08
     Women
    0.08
    Gender
    0.08
    andro
    0.08
     kvin
    0.08
     Femin
    0.08
     women
    0.08
    women
    0.07
    Activations Density 0.013%

    No Known Activations