© 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. 9-LLAMASCOPE-RES-131K
    11. 96661
    Prev
    Next
    INDEX
    Explanations

    terms related to homelessness and housing-related support services

    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
    ROLL
    -0.07
    pedia
    -0.07
    üle
    -0.07
    inho
    -0.06
    erer
    -0.06
    Äįil
    -0.06
     Toll
    -0.06
     zoekt
    -0.06
    ario
    -0.06
    ictim
    -0.06
    POSITIVE LOGITS
    irst
    0.07
    +E
    0.07
     -*-č↵
    0.06
     Westbrook
    0.06
     Facts
    0.06
    ten
    0.06
     SN
    0.06
    thouse
    0.06
     Intercept
    0.06
    elong
    0.06
    Activations Density 0.003%

    No Known Activations