© 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. 57935
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating possession or relationships

    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
    stoup
    -0.08
    icies
    -0.08
    illas
    -0.08
    erece
    -0.08
    fos
    -0.07
    icamente
    -0.07
    Ñĥз
    -0.07
    rais
    -0.07
    heiro
    -0.07
    नल
    -0.07
    POSITIVE LOGITS
     today
    0.08
    -many
    0.08
     same
    0.07
     whom
    0.07
    -times
    0.07
     times
    0.07
     already
    0.06
     these
    0.06
    obre
    0.06
    /all
    0.06
    Activations Density 0.018%

    No Known Activations