© 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. 2696
    Prev
    Next
    INDEX
    Explanations

    references to water scarcity and its impact on communities

    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
     thôi
    -0.08
    zens
    -0.07
    oleÄį
    -0.06
    _DLL
    -0.06
    å«
    -0.06
    gin
    -0.06
     Fra
    -0.06
    amaz
    -0.06
    759
    -0.06
    imus
    -0.06
    POSITIVE LOGITS
     regimes
    0.08
     during
    0.07
    198
    0.07
     Soviet
    0.07
    ucher
    0.07
     decades
    0.07
     underground
    0.07
     pitched
    0.07
     ÑĢежим
    0.07
     Cold
    0.07
    Activations Density 0.096%

    No Known Activations