© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40003
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "shortage" related to various resources or needs

    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
    atively
    -0.08
    rieg
    -0.08
    ValuePair
    -0.08
    izable
    -0.07
    aginator
    -0.07
     Rahman
    -0.07
    ifax
    -0.07
    redicate
    -0.07
    romise
    -0.07
    ially
    -0.07
    POSITIVE LOGITS
    y
    0.07
    alist
    0.07
     funds
    0.07
    /loose
    0.07
     halinde
    0.06
     supply
    0.06
    /full
    0.06
     cục
    0.06
    832
    0.06
    erer
    0.06
    Activations Density 0.010%

    No Known Activations