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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95671
    Prev
    Next
    INDEX
    Explanations

    terms related to health benefits and 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
    õi
    -0.07
    luet
    -0.07
    ronym
    -0.07
    illa
    -0.07
    egment
    -0.07
    åĪļ
    -0.07
     beneficiation
    -0.07
    .usermodel
    -0.07
    bery
    -0.07
    aro
    -0.07
    POSITIVE LOGITS
    SizePolicy
    0.07
    ÙIJر
    0.06
    etsy
    0.06
     Sanat
    0.06
     bol
    0.06
    /activity
    0.06
    IntPtr
    0.05
    AspectRatio
    0.05
     Trick
    0.05
     det
    0.05
    Activations Density 0.021%

    No Known Activations