© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126674
    Prev
    Next
    INDEX
    Explanations

    the word "likely" in various contexts

    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
    endl
    -0.06
    adian
    -0.06
    ivot
    -0.06
    vla
    -0.05
    rq
    -0.05
    linger
    -0.05
     personalized
    -0.05
    rab
    -0.05
    aylor
    -0.05
     clearly
    -0.05
    POSITIVE LOGITS
    ousel
    0.07
    ognito
    0.07
    iele
    0.07
    ewis
    0.07
    оÑĤи
    0.06
    ;y
    0.06
    æĮ¯
    0.06
    ance
    0.06
    weise
    0.06
    ëł¥ìĿĦ
    0.06
    Activations Density 0.011%

    No Known Activations