© 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 EvalsExportsinterp-engineNEWAPI 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. 104536
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    hta
    -0.07
    ulings
    -0.07
    ker
    -0.07
    teg
    -0.06
     prise
    -0.06
    endum
    -0.06
     Hint
    -0.06
    stru
    -0.06
    inery
    -0.06
    ضÙĪ
    -0.06
    POSITIVE LOGITS
    ots
    0.07
    Ñģклад
    0.06
      č↵č↵
    0.06
    vyk
    0.06
     оÑĩеÑĢедÑĮ
    0.06
     č↵č↵
    0.06
    suite
    0.06
    Painter
    0.06
    Navigator
    0.06
    UIT
    0.06
    Activations Density 0.029%

    No Known Activations