© 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. 108112
    Prev
    Next
    INDEX
    Explanations

    connections or associations involving "and" between items or quantities

    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
    /feed
    -0.07
    sdale
    -0.07
    auce
    -0.07
    tainment
    -0.07
    agara
    -0.07
    preload
    -0.07
     پا
    -0.07
    idak
    -0.06
    iband
    -0.06
    ostel
    -0.06
    POSITIVE LOGITS
     twin
    0.07
    ar
    0.07
    ische
    0.06
    idUser
    0.06
     createState
    0.06
    eso
    0.06
    ous
    0.06
    eres
    0.06
     Russell
    0.06
     sedm
    0.06
    Activations Density 0.045%

    No Known Activations