© 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. 77784
    Prev
    Next
    INDEX
    Explanations

    names of agricultural pests and diseases affecting crops

    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
    ilden
    -0.07
     Tato
    -0.07
    tryside
    -0.06
    erna
    -0.06
    eden
    -0.06
     live
    -0.06
    519
    -0.06
     fish
    -0.06
     Dyn
    -0.06
    ilde
    -0.05
    POSITIVE LOGITS
    åĵģ
    0.08
     dwar
    0.08
     رÙĤÙħ
    0.08
    BERS
    0.08
     addCriterion
    0.08
    Ãłng
    0.07
    važ
    0.07
    zcze
    0.07
    ARS
    0.07
    ãĥ¼ãĥ
    0.07
    Activations Density 0.047%

    No Known Activations