© 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. 54196
    Prev
    Next
    INDEX
    Explanations

    terms related to depletion and its effects on various systems

    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
    rike
    -0.09
    Stuff
    -0.07
    iger
    -0.07
    atical
    -0.07
    eger
    -0.07
    anna
    -0.07
    yal
    -0.07
    æĸ¹
    -0.06
    sembles
    -0.06
    æĵ
    -0.06
    POSITIVE LOGITS
     resources
    0.10
     reserves
    0.10
     exhausted
    0.08
     Resources
    0.08
     reserve
    0.08
    resources
    0.08
     exhaust
    0.08
     depleted
    0.07
     stocks
    0.07
     depletion
    0.07
    Activations Density 0.018%

    No Known Activations