© 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. 15-LLAMASCOPE-RES-131K
    11. 104438
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints and their management in computational processes

    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
    ç¦
    -0.07
    erg
    -0.06
    itoris
    -0.06
    essler
    -0.06
    _TestCase
    -0.06
    bart
    -0.06
    atürk
    -0.06
     Morse
    -0.06
    ENCY
    -0.06
    oras
    -0.06
    POSITIVE LOGITS
    lech
    0.07
    nech
    0.07
    tm
    0.06
    Æ°á»Ľ
    0.06
    оÑĢод
    0.06
    Ñijм
    0.06
     UNITED
    0.06
    ivation
    0.06
    lut
    0.06
    older
    0.06
    Activations Density 0.005%

    No Known Activations