© 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. 117451
    Prev
    Next
    INDEX
    Explanations

    quantifiable data related to agriculture and water resources

    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
    ÑĢей
    -0.07
    azor
    -0.07
    miss
    -0.07
    elan
    -0.07
    evi
    -0.06
     discrepan
    -0.06
    åĭŁ
    -0.06
    zas
    -0.06
    Invariant
    -0.06
    dra
    -0.06
    POSITIVE LOGITS
    urban
    0.07
     Capitals
    0.07
     households
    0.07
    patial
    0.06
     Village
    0.06
    ubs
    0.06
    ога
    0.06
     ç¦
    0.06
     Inputs
    0.06
     urban
    0.06
    Activations Density 0.001%

    No Known Activations