© 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. 118253
    Prev
    Next
    INDEX
    Explanations

    specific frequency measurements related to GHz and MHz in technical documents

    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
    TEL
    -0.08
    umu
    -0.07
    isser
    -0.07
    allo
    -0.07
    à¹ĭ
    -0.07
     midterm
    -0.06
    ip
    -0.06
    anza
    -0.06
    éné
    -0.06
    ton
    -0.06
    POSITIVE LOGITS
    /OR
    0.06
    sik
    0.06
     Dome
    0.06
    -long
    0.06
    æľ«
    0.06
    ideos
    0.06
    éº
    0.06
    -wide
    0.06
    Ìģ
    0.06
    ilik
    0.06
    Activations Density 0.013%

    No Known Activations