© 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. 79992
    Prev
    Next
    INDEX
    Explanations

    references to community health initiatives and the development of infrastructure for waste management

    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
     may
    -0.07
     maybe
    -0.06
     “
    -0.06
     possibly
    -0.06
    anger
    -0.06
     might
    -0.06
    nal
    -0.06
     perhaps
    -0.05
     allegedly
    -0.05
     Leer
    -0.05
    POSITIVE LOGITS
    rips
    0.07
    åħ¸
    0.07
    okit
    0.07
    vailability
    0.07
    enes
    0.07
    ìĹŃ
    0.07
    tring
    0.07
    yny
    0.07
    SCO
    0.06
    ikip
    0.06
    Activations Density 0.003%

    No Known Activations