© 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. 128224
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "http," indicating a focus on web links or URLs

    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
    acles
    -0.07
     tslib
    -0.06
     lent
    -0.06
    rze
    -0.06
    uteur
    -0.06
    aal
    -0.06
    lien
    -0.06
    opies
    -0.06
    SingleOrDefault
    -0.06
    ool
    -0.05
    POSITIVE LOGITS
    YPRE
    0.07
    itel
    0.07
    :\/\/
    0.07
     Duy
    0.07
    /port
    0.07
    UFF
    0.07
     Raq
    0.07
    LOY
    0.06
    .osgi
    0.06
    à¹ĩà¸Ńà¸ģ
    0.06
    Activations Density 0.004%

    No Known Activations