© 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. 77959
    Prev
    Next
    INDEX
    Explanations

    phrases related to various service providers across different industries

    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
    ož
    -0.09
    jvu
    -0.08
    umlu
    -0.08
    åŁ
    -0.08
    оваÑĢ
    -0.07
    oine
    -0.07
    rzy
    -0.07
    éal
    -0.07
    beck
    -0.07
    -alist
    -0.07
    POSITIVE LOGITS
     or
    0.08
     for
    0.07
    or
    0.07
     anywhere
    0.07
     either
    0.07
    for
    0.07
    igh
    0.06
    çļĦè¯Ŀ
    0.06
    is
    0.06
     trustworthy
    0.06
    Activations Density 0.011%

    No Known Activations