© 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. 125636
    Prev
    Next
    INDEX
    Explanations

    references to metrics and statistics related to governance and performance evaluation

    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
    deen
    -0.07
    innacle
    -0.06
     Caller
    -0.06
    grammar
    -0.06
    claimer
    -0.06
     milyar
    -0.06
    esso
    -0.06
    lector
    -0.06
    -preview
    -0.06
     remaining
    -0.06
    POSITIVE LOGITS
    iper
    0.07
     thôi
    0.07
    رÙģت
    0.07
    ÑĥÑĤи
    0.06
    окол
    0.06
    xCD
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
     your
    0.06
    ëĿ½
    0.06
     IMPLIED
    0.06
    Activations Density 0.003%

    No Known Activations