© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 58995
    Prev
    Next
    INDEX
    Explanations

    parts and sections of documents or articles, particularly those denoted by Roman numerals or numbers

    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
    /ros
    -0.07
    zin
    -0.06
     hete
    -0.06
    çīĮ
    -0.06
     PLUGIN
    -0.06
     indeb
    -0.06
    ukt
    -0.06
    eer
    -0.06
     Hust
    -0.06
     éc
    -0.06
    POSITIVE LOGITS
    :
    0.10
     Part
    0.07
    rored
    0.07
    acios
    0.07
     part
    0.06
    .bunifuFlatButton
    0.06
    anlı
    0.06
    alus
    0.06
    Part
    0.06
    warts
    0.06
    Activations Density 0.012%

    No Known Activations