© 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 EvalsExportsinterp-engineNEWAPI 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. 62770
    Prev
    Next
    INDEX
    Explanations

    themes related to competition and achievement 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
    nem
    -0.08
    /Runtime
    -0.08
    lug
    -0.08
    ange
    -0.08
     fır
    -0.07
    ane
    -0.07
    ánh
    -0.07
    lector
    -0.07
    Conv
    -0.06
    ëĤ
    -0.06
    POSITIVE LOGITS
     professional
    0.07
     eventually
    0.07
     professionnel
    0.07
     Dreams
    0.06
     eventual
    0.06
     пÑĢоÑĦ
    0.06
    .Binding
    0.06
     cul
    0.06
    professional
    0.06
    梦
    0.06
    Activations Density 0.010%

    No Known Activations