© 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. 72140
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental initiatives and programs

    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
     sao
    -0.07
    ÙĦØŃ
    -0.07
     misd
    -0.07
     rost
    -0.07
     bý
    -0.06
    ضÛĮ
    -0.06
     rahat
    -0.06
    Òij
    -0.06
    ç«Ł
    -0.06
     ><?
    -0.06
    POSITIVE LOGITS
    /of
    0.08
    erring
    0.08
    TM
    0.07
    enga
    0.07
    uilder
    0.07
    otch
    0.06
     Regards
    0.06
    eniable
    0.06
    exampleInputEmail
    0.06
    ccione
    0.06
    Activations Density 0.061%

    No Known Activations