© 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. 17-LLAMASCOPE-RES-131K
    6. 84923
    Prev
    Next
    INDEX
    Explanations

    instances of articles and nouns that suggest specific concepts or ideas

    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
    елик
    -0.07
     Jug
    -0.07
     trif
    -0.06
    jedn
    -0.06
    ạp
    -0.06
    ơn
    -0.06
     æ¡
    -0.06
    LI
    -0.06
    xac
    -0.06
    geries
    -0.06
    POSITIVE LOGITS
    ieber
    0.06
    iot
    0.06
    cente
    0.06
    isi
    0.06
     Hawks
    0.06
     ẩm
    0.06
    iferay
    0.06
    Cc
    0.06
    IData
    0.06
    kuk
    0.05
    Activations Density 0.009%

    No Known Activations