© 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 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. 29428
    Prev
    Next
    INDEX
    Explanations

    terms related to plants and their biological functions

    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
    vos
    -0.06
     Fragment
    -0.06
    ibase
    -0.06
    ethoven
    -0.06
    reff
    -0.06
    ibaba
    -0.06
     fragments
    -0.05
     scrub
    -0.05
    terra
    -0.05
    mez
    -0.05
    POSITIVE LOGITS
    growth
    0.08
    grow
    0.07
     growth
    0.07
    .Generated
    0.07
     Growth
    0.07
    bundle
    0.07
     Bundle
    0.07
     Bund
    0.07
    éł
    0.07
     бÑĥÑĢ
    0.07
    Activations Density 0.001%

    No Known Activations